Upload 4 files

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Nutri-Label/simfang.ttf filter=lfs diff=lfs merge=lfs -text
+simfang.ttf filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,267 @@
+import streamlit as st
+import cv2
+import numpy as np
+import re
+import os
+import pandas as pd
+from PIL import Image
+import time
+from ultralytics import YOLO
+from paddleocr import PaddleOCR, draw_ocr
+
+st.title("Nutri-Grade Label Detection & Grade Calculator")
+
+# -----------------------------------------------
+# Info & Petunjuk Penggunaan
+# -----------------------------------------------
+with st.expander("Info & Petunjuk Penggunaan"):
+    st.markdown("""
+    **Deskripsi Aplikasi:**
+
+    Aplikasi ini membantu Anda mendeteksi dan mengekstrak informasi tabel gizi dari gambar label nutrisi, melakukan normalisasi nilai nutrisi per 100 g/ml, dan menghitung Nutri-Grade sesuai dengan standar resmi (Rev. Juni 2023).
+
+    **Fitur Utama:**
+    - Deteksi objek label nutrisi dengan YOLO.
+    - Ekstraksi teks dengan PaddleOCR, mendukung format "key: value".
+    - Normalisasi nilai nutrisi (Gula dan Lemak Jenuh) per 100 g/ml.
+    - Perhitungan grade berdasarkan threshold:
+         • Gula: Grade A ≤ 1g, B: >1-5g, C: >5-10g, D: >10g per 100 ml.
+         • Lemak Jenuh: Grade A ≤ 0.7g, B: >0.7-1.2g, C: >1.2-2.8g, D: >2.8g per 100 ml.
+         • **Grade akhir diambil dari nilai terburuk antara gula dan lemak jenuh.**
+
+    **Cara Penggunaan:**
+    1. Upload gambar label nutrisi (JPG/PNG).
+    2. Sistem mendeteksi objek dan mengekstrak nilai nutrisi.
+    3. Periksa dan koreksi nilai secara manual jika diperlukan.
+    4. Klik *Hitung* untuk melihat tabel normalisasi dan grade.
+    """)
+
+with st.expander("!! Tolong Diperhatikan !!"):
+    st.markdown("""
+    Labelisasi di bawah hanya sebagai gambaran umum. Perlu riset lebih lanjut untuk akurasi.
+
+    **Pengembangan:**
+    - Konsultasi dengan nutritionist untuk parameter yang lebih tepat.
+    - Integrasi informasi halal, kalori, dan fitur interaktif (misal: chatbot).
+    """)
+
+# Fungsi untuk membersihkan nilai numerik (contoh: "15g" → 15.0)
+def parse_numeric_value(text):
+    cleaned = re.sub(r"[^\d\.\-]", "", text)
+    try:
+        return float(cleaned)
+    except ValueError:
+        return 0.0
+
+# Inisialisasi model YOLO dan PaddleOCR
+trained_model_path = "best.pt"  # Pastikan file model YOLO ada di working directory
+yolo_model = YOLO(trained_model_path)
+ocr_model = PaddleOCR(use_gpu=True, lang='en', cls=True)
+
+# --- STEP 1: Upload Gambar ---
+uploaded_file = st.file_uploader("Upload Gambar (JPG/PNG)", type=["jpg", "jpeg", "png"])
+if uploaded_file is not None:
+    file_bytes = np.asarray(bytearray(uploaded_file.read()), dtype=np.uint8)
+    img = cv2.imdecode(file_bytes, 1)
+    st.image(cv2.cvtColor(img, cv2.COLOR_BGR2RGB), caption="Gambar yang diupload", use_column_width=True)
+    img_path = "uploaded_image.jpg"
+    cv2.imwrite(img_path, img)
+
+    # --- STEP 2: Object Detection & Crop dengan YOLO ---
+    st.write("Melakukan object detection dengan YOLO dan crop region...")
+    yolo_results = yolo_model.predict(source=img_path, conf=0.5)
+    crop_images = []
+    boxes = yolo_results[0].boxes
+    for i, box in enumerate(boxes):
+        x1, y1, x2, y2 = box.xyxy[0].cpu().numpy().astype(int)
+        cropped = img[y1:y2, x1:x2]
+        crop_filename = f"crop_{i}.jpg"
+        cv2.imwrite(crop_filename, cropped)
+        crop_images.append((crop_filename, cropped))
+    st.success("Proses crop bounding box selesai!")
+    st.write("Jumlah crop yang ditemukan:", len(crop_images))
+    for crop_filename, cropped in crop_images:
+        st.image(cv2.cvtColor(cropped, cv2.COLOR_BGR2RGB), caption=f"Crop: {crop_filename}", use_column_width=True)
+
+    # --- STEP 3: OCR pada Gambar Penuh ---
+    st.write("Melakukan OCR pada gambar penuh dengan PaddleOCR...")
+    start_time = time.time()
+    ocr_result = ocr_model.ocr(img_path, cls=True)
+    ocr_time = time.time() - start_time
+    st.write(f"Waktu pemrosesan OCR: {ocr_time:.2f} detik")
+
+    if not ocr_result or len(ocr_result[0]) == 0:
+        st.error("OCR tidak menemukan teks pada gambar!")
+    else:
+        # Ekstrak data OCR
+        ocr_data = ocr_result[0]
+        ocr_list = []
+        for line in ocr_data:
+            box = line[0]
+            text = line[1][0]
+            score = line[1][1]
+            xs = [pt[0] for pt in box]
+            ys = [pt[1] for pt in box]
+            center_x = sum(xs) / len(xs)
+            center_y = sum(ys) / len(ys)
+            ocr_list.append({
+                "text": text,
+                "box": box,
+                "score": score,
+                "center_x": center_x,
+                "center_y": center_y,
+                "height": max(ys) - min(ys)
+            })
+        # Urutkan berdasarkan posisi vertikal
+        ocr_list = sorted(ocr_list, key=lambda x: x["center_y"])
+
+        # Ekstrak pasangan key-value dengan format "key: value"
+        # Hanya ekstrak gula, takaran saji, dan lemak jenuh
+        target_keys = {
+            "gula": ["gula"],
+            "takaran saji": ["takaran saji", "serving size"],
+            "lemak jenuh": ["lemak jenuh"]
+        }
+        extracted = {}
+        # Pass 1: Ekstraksi menggunakan tanda titik dua
+        for item in ocr_list:
+            txt_lower = item["text"].lower()
+            if ":" in txt_lower:
+                parts = txt_lower.split(":")
+                key_candidate = parts[0].strip()
+                value_candidate = parts[-1].strip()
+                for canonical, variants in target_keys.items():
+                    for variant in variants:
+                        if variant in key_candidate and canonical not in extracted:
+                            clean_value = re.sub(r"[^\d\.\-]", "", value_candidate)
+                            if clean_value and clean_value != ".":
+                                extracted[canonical.capitalize()] = clean_value
+                            break
+        # Pass 2: Fallback untuk key yang belum diekstrak
+        for item in ocr_list:
+            txt_lower = item["text"].lower()
+            for canonical, variants in target_keys.items():
+                if canonical not in extracted:
+                    for variant in variants:
+                        if variant in txt_lower:
+                            key_center = (item["center_x"], item["center_y"])
+                            key_height = item["height"]
+                            best_candidate = None
+                            min_dx = float('inf')
+                            for other in ocr_list:
+                                if other == item:
+                                    continue
+                                if other["center_x"] > key_center[0] and abs(other["center_y"] - key_center[1]) < 0.5 * key_height:
+                                    dx = other["center_x"] - key_center[0]
+                                    if dx < min_dx:
+                                        min_dx = dx
+                                        best_candidate = other
+                            if best_candidate:
+                                raw_value = best_candidate["text"]
+                                clean_value = re.sub(r"[^\d\.\-]", "", raw_value)
+                                if clean_value and clean_value != ".":
+                                    extracted[canonical.capitalize()] = clean_value
+                            break
+
+        if extracted:
+            st.write("**Hasil Ekstraksi Key-Value:**")
+            for k, v in extracted.items():
+                st.write(f"{k}: {v}")
+        else:
+            st.warning("Tidak ditemukan pasangan key-value yang cocok.")
+
+        # Tampilkan hasil OCR dengan bounding box untuk referensi
+        boxes_ocr = [line["box"] for line in ocr_list]
+        texts_ocr = [line["text"] for line in ocr_list]
+        scores_ocr = [line["score"] for line in ocr_list]
+        im_show = draw_ocr(Image.open(img_path).convert("RGB"), boxes_ocr, texts_ocr, scores_ocr, font_path="simfang.ttf")
+        im_show = Image.fromarray(im_show)
+        st.image(im_show, caption="Hasil OCR dengan Bounding Boxes", use_column_width=True)
+
+    # --- Koreksi Manual dengan st.form ---
+    with st.form("correction_form"):
+        st.write("Silakan koreksi nilai jika diperlukan (hanya angka, tanpa satuan):")
+        corrected_data = {}
+        for key in target_keys.keys():
+            key_cap = key.capitalize()
+            current_val = str(parse_numeric_value(extracted.get(key_cap, ""))) if key_cap in extracted else ""
+            new_val = st.text_input(f"{key_cap}", value=current_val)
+            corrected_data[key_cap] = new_val
+        submit_button = st.form_submit_button("Hitung")
+
+    if submit_button:
+        try:
+            serving_size = parse_numeric_value(corrected_data.get("Takaran saji", "100"))
+        except:
+            serving_size = 0.0
+
+        # Ambil nilai nutrisi (hanya gula dan lemak jenuh)
+        sugar_value = parse_numeric_value(corrected_data.get("Gula", "0"))
+        fat_value   = parse_numeric_value(corrected_data.get("Lemak jenuh", "0"))
+
+        if serving_size > 0:
+            sugar_norm = (sugar_value / serving_size) * 100
+            fat_norm   = (fat_value / serving_size) * 100
+        else:
+            st.error("Takaran saji tidak valid untuk normalisasi.")
+            sugar_norm, fat_norm = sugar_value, fat_value
+
+        st.write("**Tabel Hasil Normalisasi per 100 g/ml**")
+        data_tabel = {
+            "Nutrisi": ["Gula", "Lemak jenuh"],
+            "Nilai (per 100 g/ml)": [sugar_norm, fat_norm]
+        }
+        df_tabel = pd.DataFrame(data_tabel)
+        st.table(df_tabel)
+
+        # Fungsi untuk menghitung grade berdasarkan threshold
+        def grade_from_value(value, thresholds):
+            if value <= thresholds["A"]:
+                return "Grade A"
+            elif value <= thresholds["B"]:
+                return "Grade B"
+            elif value <= thresholds["C"]:
+                return "Grade C"
+            else:
+                return "Grade D"
+
+        # Threshold sesuai panduan Nutri-Grade (g/100ml)
+        thresholds_sugar = {"A": 1.0, "B": 5.0, "C": 10.0}
+        thresholds_fat   = {"A": 0.7, "B": 1.2, "C": 2.8}
+
+        sugar_grade = grade_from_value(sugar_norm, thresholds_sugar)
+        fat_grade   = grade_from_value(fat_norm, thresholds_fat)
+
+        # Grade akhir diambil dari nilai terburuk (nilai maksimum skor)
+        grade_scores = {"Grade A": 1, "Grade B": 2, "Grade C": 3, "Grade D": 4}
+        worst_score = max(grade_scores[sugar_grade], grade_scores[fat_grade])
+        inverse_scores = {v: k for k, v in grade_scores.items()}
+        final_grade = inverse_scores[worst_score]
+
+        st.write(f"**Grade Gula:** {sugar_grade}")
+        st.write(f"**Grade Lemak Jenuh:** {fat_grade}")
+        st.write(f"**Grade Akhir:** {final_grade}")
+
+        def color_grade(grade_text):
+            if grade_text == "Grade A":
+                bg_color = "#2ecc71"
+            elif grade_text == "Grade B":
+                bg_color = "#f1c40f"
+            elif grade_text == "Grade C":
+                bg_color = "#e67e22"
+            else:
+                bg_color = "#e74c3c"
+            return f"""
+            <div style="
+                background-color: {bg_color};
+                padding: 10px;
+                border-radius: 5px;
+                margin-top: 10px;
+                font-weight: bold;
+                color: white;
+                text-align: center;
+            ">
+            {grade_text}
+            </div>
+            """
+        st.markdown(color_grade(final_grade), unsafe_allow_html=True)

best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ffd3c6552428cee4cd5895053bd1ea6b1f4e7815d46bd03807c243ac75d17ca
+size 6248483

requrements.txt

@@ -0,0 +1,9 @@
+--extra-index-url=https://www.paddlepaddle.org.cn/packages/stable/cpu/
+paddlepaddle==3.0.0rc1
+paddleocr
+ultralytics
+streamlit
+numpy
+opencv-python
+pandas
+Pillow

simfang.ttf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:521c6f7546b4eb64fa4b0cd604bbd36333a20a57e388c8e2ad2ad07b9e593864
+size 10576012