Update ocr_engine.py

ocr_engine.py

@@ -2,23 +2,27 @@ import cv2
 import pytesseract
 import re
 
+# Optional: manually set Tesseract path if needed
+# pytesseract.pytesseract.tesseract_cmd = r"/usr/bin/tesseract"
+
 def extract_weight_from_image(img_cv):
     # Resize to enhance detail
     img = cv2.resize(img_cv, None, fx=2.0, fy=2.0, interpolation=cv2.INTER_CUBIC)
 
-    # Convert to grayscale
+    # Convert to grayscale if needed
     if len(img.shape) == 3:
         img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
 
-    # Apply adaptive threshold
+    # Adaptive threshold to boost OCR contrast
     img = cv2.adaptiveThreshold(img, 255, cv2.ADAPTIVE_THRESH_MEAN_C,
                                 cv2.THRESH_BINARY, 11, 3)
 
-    # OCR config
+    # OCR configuration to focus on digits and decimal points
     config = "--psm 6 -c tessedit_char_whitelist=0123456789."
+
     text = pytesseract.image_to_string(img, config=config)
 
-    # Regex match for weight
+    # Regex to extract decimal or integer weight
     matches = re.findall(r'\d+\.\d+|\d+', text)
     weight = matches[0] if matches else "0.0"
     confidence = 85 if matches else 0  # Simulated confidence