paddleocr package

.gitattributes

@@ -32,3 +32,4 @@ 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
+*.whl filter=lfs diff=lfs merge=lfs -text

app.py

@@ -1,17 +1,16 @@
 import gradio as gr
-from easyocr import Reader
-from PIL import Image
-import io
+from deprem_ocr.ocr import DepremOCR
 import json
 import csv
 import openai
 import ast
 import os
+import numpy as np
 from deta import Deta
 
 
-openai.api_key = os.getenv('API_KEY')
-reader = Reader(["tr"])
+openai.api_key = os.getenv("API_KEY")
+depremOCR = DepremOCR()
 
 
 def get_parsed_address(input_img):
@@ -20,14 +19,9 @@ def get_parsed_address(input_img):
     return openai_response(address_full_text)
 
 
-def preprocess_img(inp_image):
-    gray = cv2.cvtColor(inp_image, cv2.COLOR_BGR2GRAY)
-    gray_img = cv2.bitwise_not(gray)
-    return gray_img
-
-
 def get_text(input_img):
-    result = reader.readtext(input_img, detail=0)
+    result = depremOCR.apply_ocr(np.array(input_img))
+    print(result)
     return " ".join(result)
 
 
@@ -45,9 +39,10 @@ def get_json(mahalle, il, sokak, apartman):
     dump = json.dumps(adres, indent=4, ensure_ascii=False)
     return dump
 
+
 def write_db(data_dict):
     # 2) initialize with a project key
-    deta_key = os.getenv('DETA_KEY')
+    deta_key = os.getenv("DETA_KEY")
     deta = Deta(deta_key)
 
     # 3) create and use as many DBs as you want!
@@ -60,16 +55,17 @@ def text_dict(input):
     write_db(eval_result)
 
     return (
-        str(eval_result['city']),
-        str(eval_result['distinct']),
-        str(eval_result['neighbourhood']),
-        str(eval_result['street']),
-        str(eval_result['address']),
-        str(eval_result['tel']),
-        str(eval_result['name_surname']),
-        str(eval_result['no']),
+        str(eval_result["city"]),
+        str(eval_result["distinct"]),
+        str(eval_result["neighbourhood"]),
+        str(eval_result["street"]),
+        str(eval_result["address"]),
+        str(eval_result["tel"]),
+        str(eval_result["name_surname"]),
+        str(eval_result["no"]),
     )
-        
+
+
 def openai_response(ocr_input):
     prompt = f"""Tabular Data Extraction You are a highly intelligent and accurate tabular data extractor from 
             plain text input and especially from emergency text that carries address information, your inputs can be text 
@@ -98,28 +94,31 @@ def openai_response(ocr_input):
     resp = eval(resp.replace("'{", "{").replace("}'", "}"))
     resp["input"] = ocr_input
     dict_keys = [
-    'city',
-    'distinct',
-    'neighbourhood',
-    'street',
-    'no',
-    'tel',
-    'name_surname',
-    'address',
-    'input',
+        "city",
+        "distinct",
+        "neighbourhood",
+        "street",
+        "no",
+        "tel",
+        "name_surname",
+        "address",
+        "input",
     ]
     for key in dict_keys:
         if key not in resp.keys():
-            resp[key] = ''
+            resp[key] = ""
     return resp
 
 
 with gr.Blocks() as demo:
     gr.Markdown(
-    """
+        """
     # Enkaz Bildirme Uygulaması
-    """)
-    gr.Markdown("Bu uygulamada ekran görüntüsü sürükleyip bırakarak AFAD'a enkaz bildirimi yapabilirsiniz. Mesajı metin olarak da girebilirsiniz, tam adresi ayrıştırıp döndürür. API olarak kullanmak isterseniz sayfanın en altında use via api'ya tıklayın.")
+    """
+    )
+    gr.Markdown(
+        "Bu uygulamada ekran görüntüsü sürükleyip bırakarak AFAD'a enkaz bildirimi yapabilirsiniz. Mesajı metin olarak da girebilirsiniz, tam adresi ayrıştırıp döndürür. API olarak kullanmak isterseniz sayfanın en altında use via api'ya tıklayın."
+    )
     with gr.Row():
         img_area = gr.Image(label="Ekran Görüntüsü yükleyin 👇")
         ocr_result = gr.Textbox(label="Metin yükleyin 👇 ")
@@ -140,13 +139,23 @@ with gr.Blocks() as demo:
         with gr.Row():
             no = gr.Textbox(label="Kapı No")
 
+    submit_button.click(
+        get_parsed_address,
+        inputs=img_area,
+        outputs=open_api_text,
+        api_name="upload_image",
+    )
 
-    submit_button.click(get_parsed_address, inputs = img_area, outputs = open_api_text, api_name="upload_image")
-
-    ocr_result.change(openai_response, ocr_result, open_api_text, api_name="upload-text")
+    ocr_result.change(
+        openai_response, ocr_result, open_api_text, api_name="upload-text"
+    )
 
-    open_api_text.change(text_dict, open_api_text, [city, distinct, neighbourhood, street, address, tel, name_surname, no])
+    open_api_text.change(
+        text_dict,
+        open_api_text,
+        [city, distinct, neighbourhood, street, address, tel, name_surname, no],
+    )
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

deprem_ocr-1.0.19-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca7baccfbe8c4b0cd1b37fc022d077056dbf082bd2a352b1e8ef6d43a6f9f87
+size 11961345

requirements.txt

@@ -1,5 +1,14 @@
+paddlepaddle
+opencv-python
+Pillow
+numpy==1.23.3
+pandas
+imutils
+Cython
+imgaug
+pyclipper
+deprem_ocr-1.0.19-py3-none-any.whl
 openai
 Pillow
-easyocr
 gradio
-deta
+deta