Update ocr_engine.py

ocr_engine.py

@@ -1,43 +1,29 @@
-import easyocr
+import pytesseract
 import numpy as np
 import cv2
 import re
 
-reader = easyocr.Reader(['en'], gpu=False)
-
 def extract_weight_from_image(pil_img):
     try:
-        # Convert PIL to NumPy
+        # Convert PIL to OpenCV format
         img = np.array(pil_img)
 
-        # Step 1: Preprocessing
-        img = cv2.resize(img, None, fx=3.5, fy=3.5, interpolation=cv2.INTER_LINEAR)
+        # Resize and convert to grayscale
+        img = cv2.resize(img, None, fx=2, fy=2, interpolation=cv2.INTER_CUBIC)
         gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
 
-        # Improve contrast & threshold
-        blur = cv2.GaussianBlur(gray, (5, 5), 0)
-        _, binary = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
-        binary = cv2.bitwise_not(binary)
-
-        # Step 2: OCR with bounding boxes
-        results = reader.readtext(binary, detail=1)
-
-        # Step 3: Filter for weight-like values
-        weight_candidates = []
-        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))
+        # Thresholding for clarity
+        _, thresh = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY_INV)
 
-        if not weight_candidates:
-            return "Not detected", 0.0
+        # Run OCR
+        text = pytesseract.image_to_string(thresh)
+        print("OCR TEXT:", text)
 
-        # 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)
+        # Search for weight pattern
+        match = re.search(r"\b\d{2,4}(\.\d{1,2})?\b", text)
+        if match:
+            return match.group(), 99.0
+        return "Not detected", 0.0
 
     except Exception as e:
         return f"Error: {str(e)}", 0.0