Update ocr_engine.py

ocr_engine.py

@@ -3,39 +3,35 @@ import numpy as np
 import cv2
 import re
 
+# Load the OCR engine
 reader = easyocr.Reader(['en'], gpu=False)
 
 def extract_weight_from_image(pil_img):
     try:
+        # Convert PIL to OpenCV image (numpy array)
         img = np.array(pil_img)
 
-        # Resize and convert to grayscale
-        img = cv2.resize(img, None, fx=2.5, fy=2.5, interpolation=cv2.INTER_LINEAR)
+        # Step 1: Preprocess image for better OCR
+        img = cv2.resize(img, None, fx=3, fy=3, interpolation=cv2.INTER_LINEAR)
         gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
+        blur = cv2.GaussianBlur(gray, (3, 3), 0)
+        _, thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+        thresh = cv2.bitwise_not(thresh)  # Invert for dark digits
 
-        # Apply Gaussian blur to remove noise
-        blurred = cv2.GaussianBlur(gray, (5, 5), 0)
-
-        # Apply adaptive threshold
-        thresh = cv2.adaptiveThreshold(blurred, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
-                                       cv2.THRESH_BINARY_INV, 15, 6)
-
-        # OCR
-        results = reader.readtext(thresh)
-
-        # Debug: Print all detected text
-        print("OCR Results:", results)
+        # Step 2: Run OCR
+        results = reader.readtext(thresh, detail=1)
 
+        # Step 3: Extract numbers like 65.20 or 50
         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))
+        for bbox, text, conf in results:
+            clean = text.lower().replace("kg", "").replace("kgs", "").strip()
+            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
 
-        # Return the one with highest confidence
+        # Step 4: Choose highest confidence number
         weight, confidence = sorted(weight_candidates, key=lambda x: -x[1])[0]
         return weight, round(confidence * 100, 2)