Update ocr_engine.py

ocr_engine.py

@@ -9,33 +9,35 @@ def extract_weight_from_image(pil_img):
     try:
         img = np.array(pil_img)
 
-        # Convert to grayscale and resize
+        # Resize and convert to grayscale
+        img = cv2.resize(img, None, fx=2.5, fy=2.5, interpolation=cv2.INTER_LINEAR)
         gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
-        gray = cv2.resize(gray, None, fx=2, fy=2, interpolation=cv2.INTER_CUBIC)
 
-        # Histogram equalization and adaptive threshold
-        gray = cv2.equalizeHist(gray)
-        thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
-                                       cv2.THRESH_BINARY, 11, 2)
-        thresh = cv2.bitwise_not(thresh)
+        # Apply Gaussian blur to remove noise
+        blurred = cv2.GaussianBlur(gray, (5, 5), 0)
 
-        # OCR with bounding boxes
+        # Apply adaptive threshold
+        thresh = cv2.adaptiveThreshold(blurred, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
+                                       cv2.THRESH_BINARY_INV, 15, 6)
+
+        # OCR
         results = reader.readtext(thresh)
 
-        # Filter potential weight values
-        candidates = []
-        for (bbox, text, confidence) in results:
-            # Clean text
-            clean_text = text.replace('kg', '').strip()
-            if re.fullmatch(r"\d{2,4}(\.\d{1,2})?", clean_text):
-                candidates.append((clean_text, confidence))
+        # Debug: Print all detected text
+        print("OCR Results:", results)
+
+        weight_candidates = []
+        for _, text, conf in results:
+            text = text.lower().replace('kg', '').replace('kgs', '').strip()
+            if re.match(r'^\d{2,4}(\.\d{1,2})?$', text):
+                weight_candidates.append((text, conf))
 
-        if not candidates:
+        if not weight_candidates:
             return "Not detected", 0.0
 
-        # Choose the highest confidence match
-        best_weight, conf = sorted(candidates, key=lambda x: -x[1])[0]
-        return best_weight, round(conf, 2)
+        # Return the one with highest confidence
+        weight, confidence = sorted(weight_candidates, key=lambda x: -x[1])[0]
+        return weight, round(confidence * 100, 2)
 
     except Exception as e:
         return f"Error: {str(e)}", 0.0