Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+opencv_zoo/models/face_detection_yunet/example_outputs/largest_selfie.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,6 @@
 ---
-title: Face And License Plate Obfuscator - YuNet
-emoji: 🐢
-colorFrom: indigo
-colorTo: yellow
-sdk: gradio
-sdk_version: 3.47.0
+title: Face_and_License_Plate_Obfuscator_-_YuNet
 app_file: app.py
-pinned: false
+sdk: gradio
+sdk_version: 3.42.0
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,125 @@
+import numpy as np
+import cv2
+import gradio as gr
+
+from opencv_zoo.models.face_detection_yunet.yunet import YuNet
+from opencv_zoo.models.license_plate_detection_yunet.lpd_yunet import LPD_YuNet
+
+# Instantiate face detection YuNet
+face_model = YuNet(
+    modelPath="opencv_zoo/models/face_detection_yunet/face_detection_yunet_2023mar.onnx",
+    inputSize=[320, 320],
+    confThreshold=0.9,
+    nmsThreshold=0.3,
+    topK=5000,
+    backendId=cv2.dnn.DNN_BACKEND_OPENCV,
+    targetId=cv2.dnn.DNN_TARGET_CPU,
+)
+
+# Instantiate license plate detection YuNet
+lpd_model = LPD_YuNet(
+    modelPath="opencv_zoo/models/license_plate_detection_yunet/license_plate_detection_lpd_yunet_2023mar.onnx",
+    confThreshold=0.9,
+    nmsThreshold=0.3,
+    topK=5000,
+    keepTopK=750,
+    backendId=cv2.dnn.DNN_BACKEND_OPENCV,
+    targetId=cv2.dnn.DNN_TARGET_CPU,
+)
+
+
+def json_detections(face_results, lpd_results):
+    json_result = {}
+    json_result["faces"] = []
+    json_result["license_plates"] = []
+
+    for det in face_results if face_results is not None else []:
+        bbox = det[0:4].astype(np.int32)
+        json_result["faces"].append(
+            {
+                "xmin": int(bbox[0]),
+                "ymin": int(bbox[1]),
+                "xmax": int(bbox[0]) + int(bbox[2]),
+                "ymax": int(bbox[1]) + int(bbox[3]),
+            }
+        )
+
+    for det in lpd_results if lpd_results is not None else []:
+        bbox = det[:-1].astype(np.int32)
+        x1, y1, x2, y2, x3, y3, x4, y4 = bbox
+
+        xmin = min(x1, x2, x3, x4)
+        xmax = max(x1, x2, x3, x4)
+        ymin = min(y1, y2, y3, y4)
+        ymax = max(y1, y2, y3, y4)
+
+        json_result["license_plates"].append(
+            {
+                "xmin": int(xmin),
+                "ymin": int(ymin),
+                "xmax": int(xmax),
+                "ymax": int(ymax),
+            }
+        )
+
+    return json_result
+
+
+def overlay_results(image, face_results, lpd_results):
+    # Draw face results on the input image
+    for det in face_results if face_results is not None else []:
+        bbox = det[0:4].astype(np.int32)
+        cv2.rectangle(
+            image,
+            (bbox[0], bbox[1]),
+            (bbox[0] + bbox[2], bbox[1] + bbox[3]),
+            (0, 0, 0),
+            -1,
+        )
+
+    # Draw lpd results on the input image
+    for det in lpd_results:
+        bbox = det[:-1].astype(np.int32)
+        x1, y1, x2, y2, x3, y3, x4, y4 = bbox
+
+        # The output of this is technically a parallelogram, but we will
+        # just black out the rectangle
+        xmin = min(x1, x2, x3, x4)
+        xmax = max(x1, x2, x3, x4)
+        ymin = min(y1, y2, y3, y4)
+        ymax = max(y1, y2, y3, y4)
+
+        cv2.rectangle(image, (xmin, ymin), (xmax, ymax), (0, 0, 0), -1)
+
+    return image
+
+
+def predict(image):
+
+    h, w, _ = image.shape
+
+    # Inference
+    face_model.setInputSize([w, h])
+    lpd_model.setInputSize([w, h])
+    infer_image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+    face_results = face_model.infer(infer_image)
+    lpd_results = lpd_model.infer(infer_image)
+
+    # Process output
+    image = overlay_results(image, face_results, lpd_results)
+    json = json_detections(face_results, lpd_results)
+
+    return image, json
+
+
+demo = gr.Interface(
+    title="Face and License Plate Obfuscator - YuNet",
+    fn=predict,
+    inputs=gr.Image(type="numpy", label="Original Image"),
+    outputs=[
+        gr.Image(type="numpy", label="Output Image"),
+        gr.JSON(),
+    ],
+)
+
+demo.launch()

opencv_zoo/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

opencv_zoo/README.md

@@ -0,0 +1,112 @@
+# OpenCV Zoo and Benchmark
+
+A zoo for models tuned for OpenCV DNN with benchmarks on different platforms.
+
+Guidelines:
+
+- Install latest `opencv-python`:
+  ```shell
+  python3 -m pip install opencv-python
+  # Or upgrade to latest version
+  python3 -m pip install --upgrade opencv-python
+  ```
+- Clone this repo to download all models and demo scripts:
+  ```shell
+  # Install git-lfs from https://git-lfs.github.com/
+  git clone https://github.com/opencv/opencv_zoo && cd opencv_zoo
+  git lfs install
+  git lfs pull
+  ```
+- To run benchmarks on your hardware settings, please refer to [benchmark/README](./benchmark/README.md).
+
+## Models & Benchmark Results
+
+![](benchmark/color_table.svg?raw=true)
+
+Hardware Setup:
+
+- [Intel Core i7-12700K](https://www.intel.com/content/www/us/en/products/sku/134594/intel-core-i712700k-processor-25m-cache-up-to-5-00-ghz/specifications.html): 8 Performance-cores (3.60 GHz, turbo up to 4.90 GHz), 4 Efficient-cores (2.70 GHz, turbo up to 3.80 GHz), 20 threads.
+- [Raspberry Pi 4B](https://www.raspberrypi.com/products/raspberry-pi-4-model-b/specifications/): Broadcom BCM2711 SoC with a Quad core Cortex-A72 (ARM v8) 64-bit @ 1.5 GHz.
+- [Toybrick RV1126](https://t.rock-chips.com/en/portal.php?mod=view&aid=26): Rockchip RV1126 SoC with a quard-core ARM Cortex-A7 CPU and a 2.0 TOPs NPU.
+- [Khadas Edge 2](https://www.khadas.com/edge2): Rockchip RK3588S SoC with a CPU of 2.25 GHz Quad Core ARM Cortex-A76 + 1.8 GHz Quad Core Cortex-A55, and a 6 TOPS NPU.
+- [Horizon Sunrise X3](https://developer.horizon.ai/sunrise): an SoC from Horizon Robotics with a quad-core ARM Cortex-A53 1.2 GHz CPU and a 5 TOPS BPU (a.k.a NPU).
+- [MAIX-III AXera-Pi](https://wiki.sipeed.com/hardware/en/maixIII/ax-pi/axpi.html#Hardware): Axera AX620A SoC with a quad-core ARM Cortex-A7 CPU and a 3.6 TOPS @ int8 NPU.
+- [StarFive VisionFive 2](https://doc-en.rvspace.org/VisionFive2/Product_Brief/VisionFive_2/specification_pb.html): `StarFive JH7110` SoC with a RISC-V quad-core CPU, which can turbo up to 1.5GHz, and an GPU of model `IMG BXE-4-32 MC1` from Imagination, which has a work freq up to 600MHz.
+- [NVIDIA Jetson Nano B01](https://developer.nvidia.com/embedded/jetson-nano-developer-kit): a Quad-core ARM A57 @ 1.43 GHz CPU, and a 128-core NVIDIA Maxwell GPU.
+- [Khadas VIM3](https://www.khadas.com/vim3): Amlogic A311D SoC with a 2.2GHz Quad core ARM Cortex-A73 + 1.8GHz dual core Cortex-A53 ARM CPU, and a 5 TOPS NPU. Benchmarks are done using **per-tensor quantized** models. Follow [this guide](https://github.com/opencv/opencv/wiki/TIM-VX-Backend-For-Running-OpenCV-On-NPU) to build OpenCV with TIM-VX backend enabled.
+- [Atlas 200 DK](https://e.huawei.com/en/products/computing/ascend/atlas-200): Ascend 310 NPU with 22 TOPS @ INT8. Follow [this guide](https://github.com/opencv/opencv/wiki/Huawei-CANN-Backend) to build OpenCV with CANN backend enabled.
+- [Allwinner Nezha D1](https://d1.docs.aw-ol.com/en): Allwinner D1 SoC with a 1.0 GHz single-core RISC-V [Xuantie C906 CPU](https://www.t-head.cn/product/C906?spm=a2ouz.12986968.0.0.7bfc1384auGNPZ) with RVV 0.7.1 support. YuNet is tested for now. Visit [here](https://github.com/fengyuentau/opencv_zoo_cpp) for more details.
+
+***Important Notes***:
+
+- The data under each column of hardware setups on the above table represents the elapsed time of an inference (preprocess, forward and postprocess).
+- The time data is the mean of 10 runs after some warmup runs. Different metrics may be applied to some specific models.
+- Batch size is 1 for all benchmark results.
+- `---` represents the model is not availble to run on the device.
+- View [benchmark/config](./benchmark/config) for more details on benchmarking different models.
+
+## Some Examples
+
+Some examples are listed below. You can find more in the directory of each model!
+
+### Face Detection with [YuNet](./models/face_detection_yunet/)
+
+![largest selfie](./models/face_detection_yunet/example_outputs/largest_selfie.jpg)
+
+### Facial Expression Recognition with [Progressive Teacher](./models/facial_expression_recognition/)
+
+![fer demo](./models/facial_expression_recognition/example_outputs/selfie.jpg)
+
+### Human Segmentation with [PP-HumanSeg](./models/human_segmentation_pphumanseg/)
+
+![messi](./models/human_segmentation_pphumanseg/example_outputs/messi.jpg)
+
+### License Plate Detection with [LPD_YuNet](./models/license_plate_detection_yunet/)
+
+![license plate detection](./models/license_plate_detection_yunet/example_outputs/lpd_yunet_demo.gif)
+
+### Object Detection with [NanoDet](./models/object_detection_nanodet/) & [YOLOX](./models/object_detection_yolox/)
+
+![nanodet demo](./models/object_detection_nanodet/example_outputs/1_res.jpg)
+
+![yolox demo](./models/object_detection_yolox/example_outputs/3_res.jpg)
+
+### Object Tracking with [DaSiamRPN](./models/object_tracking_dasiamrpn/)
+
+![webcam demo](./models/object_tracking_dasiamrpn/example_outputs/dasiamrpn_demo.gif)
+
+### Palm Detection with [MP-PalmDet](./models/palm_detection_mediapipe/)
+
+![palm det](./models/palm_detection_mediapipe/example_outputs/mppalmdet_demo.gif)
+
+### Hand Pose Estimation with [MP-HandPose](models/handpose_estimation_mediapipe/)
+
+![handpose estimation](models/handpose_estimation_mediapipe/example_outputs/mphandpose_demo.webp)
+
+### Person Detection with [MP-PersonDet](./models/person_detection_mediapipe)
+
+![person det](./models/person_detection_mediapipe/example_outputs/mppersondet_demo.webp)
+
+### Pose Estimation with [MP-Pose](models/pose_estimation_mediapipe)
+
+![pose_estimation](models/pose_estimation_mediapipe/example_outputs/mpposeest_demo.webp)
+
+### QR Code Detection and Parsing with [WeChatQRCode](./models/qrcode_wechatqrcode/)
+
+![qrcode](./models/qrcode_wechatqrcode/example_outputs/wechat_qrcode_demo.gif)
+
+### Chinese Text detection [DB](./models/text_detection_db/)
+
+![mask](./models/text_detection_db/example_outputs/mask.jpg)
+
+### English Text detection [DB](./models/text_detection_db/)
+
+![gsoc](./models/text_detection_db/example_outputs/gsoc.jpg)
+
+### Text Detection with [CRNN](./models/text_recognition_crnn/)
+
+![crnn_demo](./models/text_recognition_crnn/example_outputs/CRNNCTC.gif)
+
+## License
+
+OpenCV Zoo is licensed under the [Apache 2.0 license](./LICENSE). Please refer to licenses of different models.

opencv_zoo/models/__init__.py

@@ -0,0 +1,96 @@
+from pathlib import Path
+import glob
+import os
+
+from .face_detection_yunet.yunet import YuNet
+from .text_detection_db.db import DB
+from .text_recognition_crnn.crnn import CRNN
+from .face_recognition_sface.sface import SFace
+from .image_classification_ppresnet.ppresnet import PPResNet
+from .human_segmentation_pphumanseg.pphumanseg import PPHumanSeg
+from .person_detection_mediapipe.mp_persondet import MPPersonDet
+from .pose_estimation_mediapipe.mp_pose import MPPose
+from .qrcode_wechatqrcode.wechatqrcode import WeChatQRCode
+from .object_tracking_dasiamrpn.dasiamrpn import DaSiamRPN
+from .person_reid_youtureid.youtureid import YoutuReID
+from .image_classification_mobilenet.mobilenet import MobileNet
+from .palm_detection_mediapipe.mp_palmdet import MPPalmDet
+from .handpose_estimation_mediapipe.mp_handpose import MPHandPose
+from .license_plate_detection_yunet.lpd_yunet import LPD_YuNet
+from .object_detection_nanodet.nanodet import NanoDet
+from .object_detection_yolox.yolox import YoloX
+from .facial_expression_recognition.facial_fer_model import FacialExpressionRecog
+
+class ModuleRegistery:
+    def __init__(self, name):
+        self._name = name
+        self._dict = dict()
+
+        self._base_path = Path(__file__).parent
+
+    def get(self, key):
+        '''
+        Returns a tuple with:
+        - a module handler,
+        - a list of model file paths
+        '''
+        return self._dict[key]
+
+    def register(self, item):
+        '''
+        Registers given module handler along with paths of model files
+        '''
+        # search for model files
+        model_dir = str(self._base_path / item.__module__.split(".")[1])
+        fp32_model_paths = []
+        fp16_model_paths = []
+        int8_model_paths = []
+        # onnx
+        ret_onnx = sorted(glob.glob(os.path.join(model_dir, "*.onnx")))
+        if "object_tracking" in item.__module__:
+            # object tracking models usually have multiple parts
+            fp32_model_paths = [ret_onnx]
+        else:
+            for r in ret_onnx:
+                if "int8" in r:
+                    int8_model_paths.append([r])
+                elif "fp16" in r: # exclude fp16 for now
+                    fp16_model_paths.append([r])
+                else:
+                    fp32_model_paths.append([r])
+        # caffe
+        ret_caffemodel = sorted(glob.glob(os.path.join(model_dir, "*.caffemodel")))
+        ret_prototxt = sorted(glob.glob(os.path.join(model_dir, "*.prototxt")))
+        caffe_models = []
+        for caffemodel, prototxt in zip(ret_caffemodel, ret_prototxt):
+            caffe_models += [prototxt, caffemodel]
+        if caffe_models:
+            fp32_model_paths.append(caffe_models)
+
+        all_model_paths = dict(
+            fp32=fp32_model_paths,
+            fp16=fp16_model_paths,
+            int8=int8_model_paths,
+        )
+
+        self._dict[item.__name__] = (item, all_model_paths)
+
+MODELS = ModuleRegistery('Models')
+MODELS.register(YuNet)
+MODELS.register(DB)
+MODELS.register(CRNN)
+MODELS.register(SFace)
+MODELS.register(PPResNet)
+MODELS.register(PPHumanSeg)
+MODELS.register(MPPersonDet)
+MODELS.register(MPPose)
+MODELS.register(WeChatQRCode)
+MODELS.register(DaSiamRPN)
+MODELS.register(YoutuReID)
+MODELS.register(MobileNet)
+MODELS.register(MPPalmDet)
+MODELS.register(MPHandPose)
+MODELS.register(LPD_YuNet)
+MODELS.register(NanoDet)
+MODELS.register(YoloX)
+MODELS.register(FacialExpressionRecog)

opencv_zoo/models/face_detection_yunet/CMakeLists.txt

@@ -0,0 +1,11 @@
+cmake_minimum_required(VERSION 3.24.0)
+project(opencv_zoo_face_detection_yunet)
+
+set(OPENCV_VERSION "4.8.0")
+set(OPENCV_INSTALLATION_PATH "" CACHE PATH "Where to look for OpenCV installation")
+
+# Find OpenCV
+find_package(OpenCV ${OPENCV_VERSION} REQUIRED HINTS ${OPENCV_INSTALLATION_PATH})
+
+add_executable(demo demo.cpp)
+target_link_libraries(demo ${OpenCV_LIBS})

opencv_zoo/models/face_detection_yunet/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2020 Shiqi Yu <shiqi.yu@gmail.com>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

opencv_zoo/models/face_detection_yunet/README.md

@@ -0,0 +1,67 @@
+# YuNet
+
+YuNet is a light-weight, fast and accurate face detection model, which achieves 0.834(AP_easy), 0.824(AP_medium), 0.708(AP_hard) on the WIDER Face validation set.
+
+Notes:
+
+- Model source: [here](https://github.com/ShiqiYu/libfacedetection.train/blob/a61a428929148171b488f024b5d6774f93cdbc13/tasks/task1/onnx/yunet.onnx).
+- This model can detect **faces of pixels between around 10x10 to 300x300** due to the training scheme.
+- For details on training this model, please visit https://github.com/ShiqiYu/libfacedetection.train.
+- This ONNX model has fixed input shape, but OpenCV DNN infers on the exact shape of input image. See https://github.com/opencv/opencv_zoo/issues/44 for more information.
+
+Results of accuracy evaluation with [tools/eval](../../tools/eval).
+
+| Models      | Easy AP | Medium AP | Hard AP |
+| ----------- | ------- | --------- | ------- |
+| YuNet       | 0.8871  | 0.8710    | 0.7681  |
+| YuNet quant | 0.8838  | 0.8683    | 0.7676  |
+
+\*: 'quant' stands for 'quantized'.
+
+## Demo
+
+### Python
+
+Run the following command to try the demo:
+
+```shell
+# detect on camera input
+python demo.py
+# detect on an image
+python demo.py --input /path/to/image -v
+
+# get help regarding various parameters
+python demo.py --help
+```
+
+### C++
+
+Install latest OpenCV and CMake >= 3.24.0 to get started with:
+
+```shell
+# A typical and default installation path of OpenCV is /usr/local
+cmake -B build -D OPENCV_INSTALLATION_PATH=/path/to/opencv/installation .
+cmake --build build
+
+# detect on camera input
+./build/demo
+# detect on an image
+./build/demo -i=/path/to/image -v
+# get help messages
+./build/demo -h
+```
+
+### Example outputs
+
+![webcam demo](./example_outputs/yunet_demo.gif)
+
+![largest selfie](./example_outputs/largest_selfie.jpg)
+
+## License
+
+All files in this directory are licensed under [MIT License](./LICENSE).
+
+## Reference
+
+- https://github.com/ShiqiYu/libfacedetection
+- https://github.com/ShiqiYu/libfacedetection.train

opencv_zoo/models/face_detection_yunet/demo.cpp

@@ -0,0 +1,220 @@
+#include "opencv2/opencv.hpp"
+
+#include <map>
+#include <vector>
+#include <string>
+#include <iostream>
+
+const std::map<std::string, int> str2backend{
+    {"opencv", cv::dnn::DNN_BACKEND_OPENCV}, {"cuda", cv::dnn::DNN_BACKEND_CUDA},
+    {"timvx",  cv::dnn::DNN_BACKEND_TIMVX},  {"cann", cv::dnn::DNN_BACKEND_CANN}
+};
+const std::map<std::string, int> str2target{
+    {"cpu", cv::dnn::DNN_TARGET_CPU}, {"cuda", cv::dnn::DNN_TARGET_CUDA},
+    {"npu", cv::dnn::DNN_TARGET_NPU}, {"cuda_fp16", cv::dnn::DNN_TARGET_CUDA_FP16}
+};
+
+class YuNet
+{
+public:
+    YuNet(const std::string& model_path,
+          const cv::Size& input_size = cv::Size(320, 320),
+          float conf_threshold = 0.6f,
+          float nms_threshold = 0.3f,
+          int top_k = 5000,
+          int backend_id = 0,
+          int target_id = 0)
+        : model_path_(model_path), input_size_(input_size),
+          conf_threshold_(conf_threshold), nms_threshold_(nms_threshold),
+          top_k_(top_k), backend_id_(backend_id), target_id_(target_id)
+    {
+        model = cv::FaceDetectorYN::create(model_path_, "", input_size_, conf_threshold_, nms_threshold_, top_k_, backend_id_, target_id_);
+    }
+
+    void setBackendAndTarget(int backend_id, int target_id)
+    {
+        backend_id_ = backend_id;
+        target_id_ = target_id;
+        model = cv::FaceDetectorYN::create(model_path_, "", input_size_, conf_threshold_, nms_threshold_, top_k_, backend_id_, target_id_);
+    }
+
+    /* Overwrite the input size when creating the model. Size format: [Width, Height].
+    */
+    void setInputSize(const cv::Size& input_size)
+    {
+        input_size_ = input_size;
+        model->setInputSize(input_size_);
+    }
+
+    cv::Mat infer(const cv::Mat image)
+    {
+        cv::Mat res;
+        model->detect(image, res);
+        return res;
+    }
+
+private:
+    cv::Ptr<cv::FaceDetectorYN> model;
+
+    std::string model_path_;
+    cv::Size input_size_;
+    float conf_threshold_;
+    float nms_threshold_;
+    int top_k_;
+    int backend_id_;
+    int target_id_;
+};
+
+cv::Mat visualize(const cv::Mat& image, const cv::Mat& faces, float fps = -1.f)
+{
+    static cv::Scalar box_color{0, 255, 0};
+    static std::vector<cv::Scalar> landmark_color{
+        cv::Scalar(255,   0,   0), // right eye
+        cv::Scalar(  0,   0, 255), // left eye
+        cv::Scalar(  0, 255,   0), // nose tip
+        cv::Scalar(255,   0, 255), // right mouth corner
+        cv::Scalar(  0, 255, 255)  // left mouth corner
+    };
+    static cv::Scalar text_color{0, 255, 0};
+
+    auto output_image = image.clone();
+
+    if (fps >= 0)
+    {
+        cv::putText(output_image, cv::format("FPS: %.2f", fps), cv::Point(0, 15), cv::FONT_HERSHEY_SIMPLEX, 0.5, text_color, 2);
+    }
+
+    for (int i = 0; i < faces.rows; ++i)
+    {
+        // Draw bounding boxes
+        int x1 = static_cast<int>(faces.at<float>(i, 0));
+        int y1 = static_cast<int>(faces.at<float>(i, 1));
+        int w = static_cast<int>(faces.at<float>(i, 2));
+        int h = static_cast<int>(faces.at<float>(i, 3));
+        cv::rectangle(output_image, cv::Rect(x1, y1, w, h), box_color, 2);
+
+        // Confidence as text
+        float conf = faces.at<float>(i, 14);
+        cv::putText(output_image, cv::format("%.4f", conf), cv::Point(x1, y1+12), cv::FONT_HERSHEY_DUPLEX, 0.5, text_color);
+
+        // Draw landmarks
+        for (int j = 0; j < landmark_color.size(); ++j)
+        {
+            int x = static_cast<int>(faces.at<float>(i, 2*j+4)), y = static_cast<int>(faces.at<float>(i, 2*j+5));
+            cv::circle(output_image, cv::Point(x, y), 2, landmark_color[j], 2);
+        }
+    }
+    return output_image;
+}
+
+int main(int argc, char** argv)
+{
+    cv::CommandLineParser parser(argc, argv,
+        "{help  h           |                                   | Print this message}"
+        "{input i           |                                   | Set input to a certain image, omit if using camera}"
+        "{model m           | face_detection_yunet_2023mar.onnx  | Set path to the model}"
+        "{backend b         | opencv                            | Set DNN backend}"
+        "{target t          | cpu                               | Set DNN target}"
+        "{save s            | false                             | Whether to save result image or not}"
+        "{vis v             | false                             | Whether to visualize result image or not}"
+        /* model params below*/
+        "{conf_threshold    | 0.9                               | Set the minimum confidence for the model to identify a face. Filter out faces of conf < conf_threshold}"
+        "{nms_threshold     | 0.3                               | Set the threshold to suppress overlapped boxes. Suppress boxes if IoU(box1, box2) >= nms_threshold, the one of higher score is kept.}"
+        "{top_k             | 5000                              | Keep top_k bounding boxes before NMS. Set a lower value may help speed up postprocessing.}"
+    );
+    if (parser.has("help"))
+    {
+        parser.printMessage();
+        return 0;
+    }
+
+    std::string input_path = parser.get<std::string>("input");
+    std::string model_path = parser.get<std::string>("model");
+    std::string backend = parser.get<std::string>("backend");
+    std::string target = parser.get<std::string>("target");
+    bool save_flag = parser.get<bool>("save");
+    bool vis_flag = parser.get<bool>("vis");
+
+    // model params
+    float conf_threshold = parser.get<float>("conf_threshold");
+    float nms_threshold = parser.get<float>("nms_threshold");
+    int top_k = parser.get<int>("top_k");
+    const int backend_id = str2backend.at(backend);
+    const int target_id = str2target.at(target);
+
+    // Instantiate YuNet
+    YuNet model(model_path, cv::Size(320, 320), conf_threshold, nms_threshold, top_k, backend_id, target_id);
+
+    // If input is an image
+    if (!input_path.empty())
+    {
+        auto image = cv::imread(input_path);
+
+        // Inference
+        model.setInputSize(image.size());
+        auto faces = model.infer(image);
+
+        // Print faces
+        std::cout << cv::format("%d faces detected:\n", faces.rows);
+        for (int i = 0; i < faces.rows; ++i)
+        {
+            int x1 = static_cast<int>(faces.at<float>(i, 0));
+            int y1 = static_cast<int>(faces.at<float>(i, 1));
+            int w = static_cast<int>(faces.at<float>(i, 2));
+            int h = static_cast<int>(faces.at<float>(i, 3));
+            float conf = faces.at<float>(i, 14);
+            std::cout << cv::format("%d: x1=%d, y1=%d, w=%d, h=%d, conf=%.4f\n", i, x1, y1, w, h, conf);
+        }
+
+        // Draw reults on the input image
+        if (save_flag || vis_flag)
+        {
+            auto res_image = visualize(image, faces);
+            if (save_flag)
+            {
+                std::cout << "Results are saved to result.jpg\n";
+                cv::imwrite("result.jpg", res_image);
+            }
+            if (vis_flag)
+            {
+                cv::namedWindow(input_path, cv::WINDOW_AUTOSIZE);
+                cv::imshow(input_path, res_image);
+                cv::waitKey(0);
+            }
+        }
+    }
+    else // Call default camera
+    {
+        int device_id = 0;
+        auto cap = cv::VideoCapture(device_id);
+        int w = static_cast<int>(cap.get(cv::CAP_PROP_FRAME_WIDTH));
+        int h = static_cast<int>(cap.get(cv::CAP_PROP_FRAME_HEIGHT));
+        model.setInputSize(cv::Size(w, h));
+
+        auto tick_meter = cv::TickMeter();
+        cv::Mat frame;
+        while (cv::waitKey(1) < 0)
+        {
+            bool has_frame = cap.read(frame);
+            if (!has_frame)
+            {
+                std::cout << "No frames grabbed! Exiting ...\n";
+                break;
+            }
+
+            // Inference
+            tick_meter.start();
+            cv::Mat faces = model.infer(frame);
+            tick_meter.stop();
+
+            // Draw results on the input image
+            auto res_image = visualize(frame, faces, (float)tick_meter.getFPS());
+            // Visualize in a new window
+            cv::imshow("YuNet Demo", res_image);
+
+            tick_meter.reset();
+        }
+    }
+
+    return 0;
+}

opencv_zoo/models/face_detection_yunet/demo.py

@@ -0,0 +1,145 @@
+# This file is part of OpenCV Zoo project.
+# It is subject to the license terms in the LICENSE file found in the same directory.
+#
+# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
+# Third party copyrights are property of their respective owners.
+
+import argparse
+
+import numpy as np
+import cv2 as cv
+
+from yunet import YuNet
+
+# Check OpenCV version
+assert cv.__version__ >= "4.8.0", \
+       "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
+
+# Valid combinations of backends and targets
+backend_target_pairs = [
+    [cv.dnn.DNN_BACKEND_OPENCV, cv.dnn.DNN_TARGET_CPU],
+    [cv.dnn.DNN_BACKEND_CUDA,   cv.dnn.DNN_TARGET_CUDA],
+    [cv.dnn.DNN_BACKEND_CUDA,   cv.dnn.DNN_TARGET_CUDA_FP16],
+    [cv.dnn.DNN_BACKEND_TIMVX,  cv.dnn.DNN_TARGET_NPU],
+    [cv.dnn.DNN_BACKEND_CANN,   cv.dnn.DNN_TARGET_NPU]
+]
+
+parser = argparse.ArgumentParser(description='YuNet: A Fast and Accurate CNN-based Face Detector (https://github.com/ShiqiYu/libfacedetection).')
+parser.add_argument('--input', '-i', type=str,
+                    help='Usage: Set input to a certain image, omit if using camera.')
+parser.add_argument('--model', '-m', type=str, default='face_detection_yunet_2023mar.onnx',
+                    help="Usage: Set model type, defaults to 'face_detection_yunet_2023mar.onnx'.")
+parser.add_argument('--backend_target', '-bt', type=int, default=0,
+                    help='''Choose one of the backend-target pair to run this demo:
+                        {:d}: (default) OpenCV implementation + CPU,
+                        {:d}: CUDA + GPU (CUDA),
+                        {:d}: CUDA + GPU (CUDA FP16),
+                        {:d}: TIM-VX + NPU,
+                        {:d}: CANN + NPU
+                    '''.format(*[x for x in range(len(backend_target_pairs))]))
+parser.add_argument('--conf_threshold', type=float, default=0.9,
+                    help='Usage: Set the minimum needed confidence for the model to identify a face, defauts to 0.9. Smaller values may result in faster detection, but will limit accuracy. Filter out faces of confidence < conf_threshold.')
+parser.add_argument('--nms_threshold', type=float, default=0.3,
+                    help='Usage: Suppress bounding boxes of iou >= nms_threshold. Default = 0.3.')
+parser.add_argument('--top_k', type=int, default=5000,
+                    help='Usage: Keep top_k bounding boxes before NMS.')
+parser.add_argument('--save', '-s', action='store_true',
+                    help='Usage: Specify to save file with results (i.e. bounding box, confidence level). Invalid in case of camera input.')
+parser.add_argument('--vis', '-v', action='store_true',
+                    help='Usage: Specify to open a new window to show results. Invalid in case of camera input.')
+args = parser.parse_args()
+
+def visualize(image, results, box_color=(0, 255, 0), text_color=(0, 0, 255), fps=None):
+    output = image.copy()
+    landmark_color = [
+        (255,   0,   0), # right eye
+        (  0,   0, 255), # left eye
+        (  0, 255,   0), # nose tip
+        (255,   0, 255), # right mouth corner
+        (  0, 255, 255)  # left mouth corner
+    ]
+
+    if fps is not None:
+        cv.putText(output, 'FPS: {:.2f}'.format(fps), (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, text_color)
+
+    for det in (results if results is not None else []):
+        bbox = det[0:4].astype(np.int32)
+        cv.rectangle(output, (bbox[0], bbox[1]), (bbox[0]+bbox[2], bbox[1]+bbox[3]), box_color, 2)
+
+        conf = det[-1]
+        cv.putText(output, '{:.4f}'.format(conf), (bbox[0], bbox[1]+12), cv.FONT_HERSHEY_DUPLEX, 0.5, text_color)
+
+        landmarks = det[4:14].astype(np.int32).reshape((5,2))
+        for idx, landmark in enumerate(landmarks):
+            cv.circle(output, landmark, 2, landmark_color[idx], 2)
+
+    return output
+
+if __name__ == '__main__':
+    backend_id = backend_target_pairs[args.backend_target][0]
+    target_id = backend_target_pairs[args.backend_target][1]
+
+    # Instantiate YuNet
+    model = YuNet(modelPath=args.model,
+                  inputSize=[320, 320],
+                  confThreshold=args.conf_threshold,
+                  nmsThreshold=args.nms_threshold,
+                  topK=args.top_k,
+                  backendId=backend_id,
+                  targetId=target_id)
+
+    # If input is an image
+    if args.input is not None:
+        image = cv.imread(args.input)
+        h, w, _ = image.shape
+
+        # Inference
+        model.setInputSize([w, h])
+        results = model.infer(image)
+
+        # Print results
+        print('{} faces detected.'.format(results.shape[0]))
+        for idx, det in enumerate(results):
+            print('{}: {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f}'.format(
+                idx, *det[:-1])
+            )
+
+        # Draw results on the input image
+        image = visualize(image, results)
+
+        # Save results if save is true
+        if args.save:
+            print('Resutls saved to result.jpg\n')
+            cv.imwrite('result.jpg', image)
+
+        # Visualize results in a new window
+        if args.vis:
+            cv.namedWindow(args.input, cv.WINDOW_AUTOSIZE)
+            cv.imshow(args.input, image)
+            cv.waitKey(0)
+    else: # Omit input to call default camera
+        deviceId = 0
+        cap = cv.VideoCapture(deviceId)
+        w = int(cap.get(cv.CAP_PROP_FRAME_WIDTH))
+        h = int(cap.get(cv.CAP_PROP_FRAME_HEIGHT))
+        model.setInputSize([w, h])
+
+        tm = cv.TickMeter()
+        while cv.waitKey(1) < 0:
+            hasFrame, frame = cap.read()
+            if not hasFrame:
+                print('No frames grabbed!')
+                break
+
+            # Inference
+            tm.start()
+            results = model.infer(frame) # results is a tuple
+            tm.stop()
+
+            # Draw results on the input image
+            frame = visualize(frame, results, fps=tm.getFPS())
+
+            # Visualize results in a new Window
+            cv.imshow('YuNet Demo', frame)
+
+            tm.reset()

opencv_zoo/models/face_detection_yunet/face_detection_yunet_2023mar.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f2383e4dd3cfbb4553ea8718107fc0423210dc964f9f4280604804ed2552fa4
+size 232589

opencv_zoo/models/face_detection_yunet/face_detection_yunet_2023mar_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:321aa5a6afabf7ecc46a3d06bfab2b579dc96eb5c3be7edd365fa04502ad9294
+size 100416

opencv_zoo/models/face_detection_yunet/yunet.py

@@ -0,0 +1,55 @@
+# This file is part of OpenCV Zoo project.
+# It is subject to the license terms in the LICENSE file found in the same directory.
+#
+# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
+# Third party copyrights are property of their respective owners.
+
+from itertools import product
+
+import numpy as np
+import cv2 as cv
+
+class YuNet:
+    def __init__(self, modelPath, inputSize=[320, 320], confThreshold=0.6, nmsThreshold=0.3, topK=5000, backendId=0, targetId=0):
+        self._modelPath = modelPath
+        self._inputSize = tuple(inputSize) # [w, h]
+        self._confThreshold = confThreshold
+        self._nmsThreshold = nmsThreshold
+        self._topK = topK
+        self._backendId = backendId
+        self._targetId = targetId
+
+        self._model = cv.FaceDetectorYN.create(
+            model=self._modelPath,
+            config="",
+            input_size=self._inputSize,
+            score_threshold=self._confThreshold,
+            nms_threshold=self._nmsThreshold,
+            top_k=self._topK,
+            backend_id=self._backendId,
+            target_id=self._targetId)
+
+    @property
+    def name(self):
+        return self.__class__.__name__
+
+    def setBackendAndTarget(self, backendId, targetId):
+        self._backendId = backendId
+        self._targetId = targetId
+        self._model = cv.FaceDetectorYN.create(
+            model=self._modelPath,
+            config="",
+            input_size=self._inputSize,
+            score_threshold=self._confThreshold,
+            nms_threshold=self._nmsThreshold,
+            top_k=self._topK,
+            backend_id=self._backendId,
+            target_id=self._targetId)
+
+    def setInputSize(self, input_size):
+        self._model.setInputSize(tuple(input_size))
+
+    def infer(self, image):
+        # Forward
+        faces = self._model.detect(image)
+        return faces[1]

opencv_zoo/models/license_plate_detection_yunet/LICENSE

@@ -0,0 +1,203 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright (c) 2022 WATRIX
+   Author: Dong Xu
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

opencv_zoo/models/license_plate_detection_yunet/README.md

@@ -0,0 +1,30 @@
+# License Plate Detection with YuNet
+
+This model is contributed by Dong Xu (徐栋) from [watrix.ai](watrix.ai) (银河水滴).
+
+Please note that the model is trained with Chinese license plates, so the detection results of other license plates with this model may be limited.
+
+## Demo
+
+Run the following command to try the demo:
+
+```shell
+# detect on camera input
+python demo.py
+# detect on an image
+python demo.py --input /path/to/image -v
+# get help regarding various parameters
+python demo.py --help
+```
+
+### Example outputs
+
+![lpd](./example_outputs/lpd_yunet_demo.gif)
+
+## License
+
+All files in this directory are licensed under [Apache 2.0 License](./LICENSE)
+
+## Reference
+
+- https://github.com/ShiqiYu/libfacedetection.train

opencv_zoo/models/license_plate_detection_yunet/demo.py

@@ -0,0 +1,129 @@
+import argparse
+
+import numpy as np
+import cv2 as cv
+
+from lpd_yunet import LPD_YuNet
+
+# Check OpenCV version
+assert cv.__version__ >= "4.8.0", \
+       "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
+
+# Valid combinations of backends and targets
+backend_target_pairs = [
+    [cv.dnn.DNN_BACKEND_OPENCV, cv.dnn.DNN_TARGET_CPU],
+    [cv.dnn.DNN_BACKEND_CUDA,   cv.dnn.DNN_TARGET_CUDA],
+    [cv.dnn.DNN_BACKEND_CUDA,   cv.dnn.DNN_TARGET_CUDA_FP16],
+    [cv.dnn.DNN_BACKEND_TIMVX,  cv.dnn.DNN_TARGET_NPU],
+    [cv.dnn.DNN_BACKEND_CANN,   cv.dnn.DNN_TARGET_NPU]
+]
+
+parser = argparse.ArgumentParser(description='LPD-YuNet for License Plate Detection')
+parser.add_argument('--input', '-i', type=str,
+                    help='Usage: Set path to the input image. Omit for using default camera.')
+parser.add_argument('--model', '-m', type=str, default='license_plate_detection_lpd_yunet_2023mar.onnx',
+                    help='Usage: Set model path, defaults to license_plate_detection_lpd_yunet_2023mar.onnx.')
+parser.add_argument('--backend_target', '-bt', type=int, default=0,
+                    help='''Choose one of the backend-target pair to run this demo:
+                        {:d}: (default) OpenCV implementation + CPU,
+                        {:d}: CUDA + GPU (CUDA),
+                        {:d}: CUDA + GPU (CUDA FP16),
+                        {:d}: TIM-VX + NPU,
+                        {:d}: CANN + NPU
+                    '''.format(*[x for x in range(len(backend_target_pairs))]))
+parser.add_argument('--conf_threshold', type=float, default=0.9,
+                    help='Usage: Set the minimum needed confidence for the model to identify a license plate, defaults to 0.9. Smaller values may result in faster detection, but will limit accuracy. Filter out faces of confidence < conf_threshold.')
+parser.add_argument('--nms_threshold', type=float, default=0.3,
+                    help='Usage: Suppress bounding boxes of iou >= nms_threshold. Default = 0.3. Suppress bounding boxes of iou >= nms_threshold.')
+parser.add_argument('--top_k', type=int, default=5000,
+                    help='Usage: Keep top_k bounding boxes before NMS.')
+parser.add_argument('--keep_top_k', type=int, default=750,
+                    help='Usage: Keep keep_top_k bounding boxes after NMS.')
+parser.add_argument('--save', '-s', action='store_true',
+                    help='Usage: Specify to save file with results (i.e. bounding box, confidence level). Invalid in case of camera input.')
+parser.add_argument('--vis', '-v', action='store_true',
+                    help='Usage: Specify to open a new window to show results. Invalid in case of camera input.')
+args = parser.parse_args()
+
+def visualize(image, dets, line_color=(0, 255, 0), text_color=(0, 0, 255), fps=None):
+    output = image.copy()
+
+    if fps is not None:
+        cv.putText(output, 'FPS: {:.2f}'.format(fps), (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, text_color)
+
+    for det in dets:
+        bbox = det[:-1].astype(np.int32)
+        x1, y1, x2, y2, x3, y3, x4, y4 = bbox
+
+        # Draw the border of license plate
+        cv.line(output, (x1, y1), (x2, y2), line_color, 2)
+        cv.line(output, (x2, y2), (x3, y3), line_color, 2)
+        cv.line(output, (x3, y3), (x4, y4), line_color, 2)
+        cv.line(output, (x4, y4), (x1, y1), line_color, 2)
+
+    return output
+
+if __name__ == '__main__':
+    backend_id = backend_target_pairs[args.backend_target][0]
+    target_id = backend_target_pairs[args.backend_target][1]
+
+    # Instantiate LPD-YuNet
+    model = LPD_YuNet(modelPath=args.model,
+                      confThreshold=args.conf_threshold,
+                      nmsThreshold=args.nms_threshold,
+                      topK=args.top_k,
+                      keepTopK=args.keep_top_k,
+                      backendId=backend_id,
+                      targetId=target_id)
+
+    # If input is an image
+    if args.input is not None:
+        image = cv.imread(args.input)
+        h, w, _ = image.shape
+
+        # Inference
+        model.setInputSize([w, h])
+        results = model.infer(image)
+
+        # Print results
+        print('{} license plates detected.'.format(results.shape[0]))
+
+        # Draw results on the input image
+        image = visualize(image, results)
+
+        # Save results if save is true
+        if args.save:
+            print('Resutls saved to result.jpg')
+            cv.imwrite('result.jpg', image)
+
+        # Visualize results in a new window
+        if args.vis:
+            cv.namedWindow(args.input, cv.WINDOW_AUTOSIZE)
+            cv.imshow(args.input, image)
+            cv.waitKey(0)
+    else: # Omit input to call default camera
+        deviceId = 0
+        cap = cv.VideoCapture(deviceId)
+        w = int(cap.get(cv.CAP_PROP_FRAME_WIDTH))
+        h = int(cap.get(cv.CAP_PROP_FRAME_HEIGHT))
+        model.setInputSize([w, h])
+
+        tm = cv.TickMeter()
+        while cv.waitKey(1) < 0:
+            hasFrame, frame = cap.read()
+            if not hasFrame:
+                print('No frames grabbed!')
+                break
+
+            # Inference
+            tm.start()
+            results = model.infer(frame) # results is a tuple
+            tm.stop()
+
+            # Draw results on the input image
+            frame = visualize(frame, results, fps=tm.getFPS())
+
+            # Visualize results in a new Window
+            cv.imshow('LPD-YuNet Demo', frame)
+
+            tm.reset()

opencv_zoo/models/license_plate_detection_yunet/license_plate_detection_lpd_yunet_2023mar.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4978a7b6d25514d5e24811b82bfb511d166bdd8ca3b03aa63c1623d4d039c7
+size 4146213

opencv_zoo/models/license_plate_detection_yunet/license_plate_detection_lpd_yunet_2023mar_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d67982a014fe93ad04612f565ed23ca010dcb0fd925d880ef0edf9cd7bdf931a
+size 1087142

opencv_zoo/models/license_plate_detection_yunet/lpd_yunet.py

@@ -0,0 +1,133 @@
+from itertools import product
+
+import numpy as np
+import cv2 as cv
+
+class LPD_YuNet:
+    def __init__(self, modelPath, inputSize=[320, 240], confThreshold=0.8, nmsThreshold=0.3, topK=5000, keepTopK=750, backendId=0, targetId=0):
+        self.model_path = modelPath
+        self.input_size = np.array(inputSize)
+        self.confidence_threshold=confThreshold
+        self.nms_threshold = nmsThreshold
+        self.top_k = topK
+        self.keep_top_k = keepTopK
+        self.backend_id = backendId
+        self.target_id = targetId
+
+        self.output_names = ['loc', 'conf', 'iou']
+        self.min_sizes = [[10, 16, 24], [32, 48], [64, 96], [128, 192, 256]]
+        self.steps = [8, 16, 32, 64]
+        self.variance = [0.1, 0.2]
+
+        # load model
+        self.model = cv.dnn.readNet(self.model_path)
+        # generate anchors/priorboxes
+        self._priorGen()
+
+    @property
+    def name(self):
+        return self.__class__.__name__
+
+    def setBackendAndTarget(self, backendId, targetId):
+        self.backend_id = backendId
+        self.target_id = targetId
+        self.model.setPreferableBackend(self.backend_id)
+        self.model.setPreferableTarget(self.target_id)
+
+    def setInputSize(self, inputSize):
+        self.input_size = inputSize
+        # re-generate anchors/priorboxes
+        self._priorGen()
+
+    def _preprocess(self, image):
+        return cv.dnn.blobFromImage(image)
+
+    def infer(self, image):
+        assert image.shape[0] == self.input_size[1], '{} (height of input image) != {} (preset height)'.format(image.shape[0], self.input_size[1])
+        assert image.shape[1] == self.input_size[0], '{} (width of input image) != {} (preset width)'.format(image.shape[1], self.input_size[0])
+
+        # Preprocess
+        inputBlob = self._preprocess(image)
+
+        # Forward
+        self.model.setInput(inputBlob)
+        outputBlob = self.model.forward(self.output_names)
+
+        # Postprocess
+        results = self._postprocess(outputBlob)
+
+        return results
+
+    def _postprocess(self, blob):
+        # Decode
+        dets = self._decode(blob)
+
+        # NMS
+        keepIdx = cv.dnn.NMSBoxes(
+            bboxes=dets[:, 0:4].tolist(),
+            scores=dets[:, -1].tolist(),
+            score_threshold=self.confidence_threshold,
+            nms_threshold=self.nms_threshold,
+            top_k=self.top_k
+        ) # box_num x class_num
+        if len(keepIdx) > 0:
+            dets = dets[keepIdx]
+            return dets[:self.keep_top_k]
+        else:
+            return np.empty(shape=(0, 9))
+
+    def _priorGen(self):
+        w, h = self.input_size
+        feature_map_2th = [int(int((h + 1) / 2) / 2),
+                           int(int((w + 1) / 2) / 2)]
+        feature_map_3th = [int(feature_map_2th[0] / 2),
+                           int(feature_map_2th[1] / 2)]
+        feature_map_4th = [int(feature_map_3th[0] / 2),
+                           int(feature_map_3th[1] / 2)]
+        feature_map_5th = [int(feature_map_4th[0] / 2),
+                           int(feature_map_4th[1] / 2)]
+        feature_map_6th = [int(feature_map_5th[0] / 2),
+                           int(feature_map_5th[1] / 2)]
+
+        feature_maps = [feature_map_3th, feature_map_4th,
+                        feature_map_5th, feature_map_6th]
+
+        priors = []
+        for k, f in enumerate(feature_maps):
+            min_sizes = self.min_sizes[k]
+            for i, j in product(range(f[0]), range(f[1])): # i->h, j->w
+                for min_size in min_sizes:
+                    s_kx = min_size / w
+                    s_ky = min_size / h
+
+                    cx = (j + 0.5) * self.steps[k] / w
+                    cy = (i + 0.5) * self.steps[k] / h
+
+                    priors.append([cx, cy, s_kx, s_ky])
+        self.priors = np.array(priors, dtype=np.float32)
+
+    def _decode(self, blob):
+        loc, conf, iou = blob
+        # get score
+        cls_scores = conf[:, 1]
+        iou_scores = iou[:, 0]
+        # clamp
+        _idx = np.where(iou_scores < 0.)
+        iou_scores[_idx] = 0.
+        _idx = np.where(iou_scores > 1.)
+        iou_scores[_idx] = 1.
+        scores = np.sqrt(cls_scores * iou_scores)
+        scores = scores[:, np.newaxis]
+
+        scale = self.input_size
+
+        # get four corner points for bounding box
+        bboxes = np.hstack((
+            (self.priors[:, 0:2] + loc[:,  4: 6] * self.variance[0] * self.priors[:, 2:4]) * scale,
+            (self.priors[:, 0:2] + loc[:,  6: 8] * self.variance[0] * self.priors[:, 2:4]) * scale,
+            (self.priors[:, 0:2] + loc[:, 10:12] * self.variance[0] * self.priors[:, 2:4]) * scale,
+            (self.priors[:, 0:2] + loc[:, 12:14] * self.variance[0] * self.priors[:, 2:4]) * scale
+        ))
+
+        dets = np.hstack((bboxes, scores))
+        return dets

requirements.txt

@@ -0,0 +1,2 @@
+opencv-python-headless
+numpy