Update ocr_engine.py

ocr_engine.py

@@ -7,38 +7,37 @@ reader = easyocr.Reader(['en'], gpu=False)
 
 def extract_weight_from_image(pil_img):
     try:
+        # Convert PIL to NumPy
         img = np.array(pil_img)
 
-        # STEP 1: Resize and convert to grayscale
-        img = cv2.resize(img, None, fx=4, fy=4, interpolation=cv2.INTER_CUBIC)
+        # Step 1: Preprocessing
+        img = cv2.resize(img, None, fx=3.5, fy=3.5, interpolation=cv2.INTER_LINEAR)
         gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
 
-        # STEP 2: Denoise + Threshold
+        # Improve contrast & threshold
         blur = cv2.GaussianBlur(gray, (5, 5), 0)
-        _, thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+        _, binary = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+        binary = cv2.bitwise_not(binary)
 
-        # Invert to get black text on white background
-        inverted = cv2.bitwise_not(thresh)
+        # Step 2: OCR with bounding boxes
+        results = reader.readtext(binary, detail=1)
 
-        # STEP 3: OCR
-        results = reader.readtext(inverted)
-
-        # Debug print
-        print("OCR Results:", results)
-
-        # STEP 4: Extract weight values using regex
+        # Step 3: Filter for weight-like values
         weight_candidates = []
-        for _, text, conf in results:
-            text = text.replace("kg", "").replace("KG", "").strip()
-            if re.match(r"^\d{2,4}(\.\d{1,2})?$", text):
-                weight_candidates.append((text, conf))
+        for bbox, text, conf in results:
+            clean = text.lower().replace("kg", "").replace("kgs", "").strip()
+            clean = clean.replace("o", "0").replace("O", "0")  # common OCR mistake
+
+            # Match like 2 digits or 3 digits or decimal numbers
+            if re.fullmatch(r"\d{2,4}(\.\d{1,2})?", clean):
+                weight_candidates.append((clean, conf))
 
         if not weight_candidates:
             return "Not detected", 0.0
 
-        # STEP 5: Highest confidence
-        weight, confidence = sorted(weight_candidates, key=lambda x: -x[1])[0]
-        return weight, round(confidence * 100, 2)
+        # Step 4: Pick most confident
+        best_weight, best_conf = sorted(weight_candidates, key=lambda x: -x[1])[0]
+        return best_weight, round(best_conf * 100, 2)
 
     except Exception as e:
         return f"Error: {str(e)}", 0.0