Update ocr_engine.py

ocr_engine.py

@@ -3,35 +3,40 @@ 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)
 
-        # Step 1: Preprocess image for better OCR
-        img = cv2.resize(img, None, fx=3, fy=3, interpolation=cv2.INTER_LINEAR)
+        # STEP 1: Resize and convert to grayscale
+        img = cv2.resize(img, None, fx=4, fy=4, interpolation=cv2.INTER_CUBIC)
         gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
-        blur = cv2.GaussianBlur(gray, (3, 3), 0)
+
+        # STEP 2: Denoise + Threshold
+        blur = cv2.GaussianBlur(gray, (5, 5), 0)
         _, thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
-        thresh = cv2.bitwise_not(thresh)  # Invert for dark digits
 
-        # Step 2: Run OCR
-        results = reader.readtext(thresh, detail=1)
+        # Invert to get black text on white background
+        inverted = cv2.bitwise_not(thresh)
+
+        # STEP 3: OCR
+        results = reader.readtext(inverted)
+
+        # Debug print
+        print("OCR Results:", results)
 
-        # Step 3: Extract numbers like 65.20 or 50
+        # STEP 4: Extract weight values using regex
         weight_candidates = []
-        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))
+        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))
 
         if not weight_candidates:
             return "Not detected", 0.0
 
-        # Step 4: Choose highest confidence number
+        # STEP 5: Highest confidence
         weight, confidence = sorted(weight_candidates, key=lambda x: -x[1])[0]
         return weight, round(confidence * 100, 2)