Update ocr_engine.py

ocr_engine.py

@@ -1,7 +1,7 @@
 import easyocr
 import numpy as np
-import re
 import cv2
+import re
 
 reader = easyocr.Reader(['en'], gpu=False)
 
@@ -9,37 +9,27 @@ def extract_weight_from_image(pil_img):
     try:
         img = np.array(pil_img)
 
-        # Convert to grayscale
+        # Grayscale + resize
         gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
+        gray = cv2.resize(gray, None, fx=2, fy=2, interpolation=cv2.INTER_CUBIC)
 
-        # Apply bilateral filter to reduce noise while keeping edges
-        filtered = cv2.bilateralFilter(gray, 11, 17, 17)
-
-        # Apply binary threshold
-        _, thresh = cv2.threshold(filtered, 150, 255, cv2.THRESH_BINARY_INV)
-
-        # Find contours
-        contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
-
-        if not contours:
-            return "No weight detected", 0.0
+        # Histogram equalization
+        gray = cv2.equalizeHist(gray)
 
-        # Get the largest contour assuming it's the display area
-        largest_contour = max(contours, key=cv2.contourArea)
-        x, y, w, h = cv2.boundingRect(largest_contour)
+        # Adaptive threshold
+        thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
+                                       cv2.THRESH_BINARY, 11, 2)
 
-        # Add padding
-        pad = 10
-        x, y = max(x - pad, 0), max(y - pad, 0)
-        cropped = gray[y:y+h+pad, x:x+w+pad]
+        # Invert colors (LCD digits are usually dark on light)
+        thresh = cv2.bitwise_not(thresh)
 
-        # OCR on cropped area
-        result = reader.readtext(cropped, detail=0)
-        combined = " ".join(result)
-        print("Detected Text:", combined)
+        # OCR
+        result = reader.readtext(thresh, detail=0)
+        combined_text = " ".join(result)
+        print("OCR Text:", combined_text)
 
-        # Match weight patterns like 52.30 or 003.25
-        match = re.search(r"\b\d{2,4}\.?\d{0,2}\b", combined)
+        # Match weight pattern (e.g. 52.30, 003.2, 250)
+        match = re.search(r"\b\d{2,4}\.?\d{0,2}\b", combined_text)
         if match:
             return match.group(), 95.0
         else: