Update ocr_engine.py

ocr_engine.py

@@ -1,8 +1,19 @@
+import easyocr
+import numpy as np
+import cv2
+import re
+
+reader = easyocr.Reader(['en'], gpu=False)
+
 def extract_weight_from_image(pil_img):
     try:
         img = np.array(pil_img)
+
+        # Resize and grayscale
         img = cv2.resize(img, None, fx=3.5, fy=3.5, interpolation=cv2.INTER_LINEAR)
         gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
+
+        # Denoise and threshold
         gray = cv2.bilateralFilter(gray, 11, 17, 17)
         thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
                                        cv2.THRESH_BINARY_INV, 11, 2)
@@ -12,11 +23,13 @@ def extract_weight_from_image(pil_img):
 
         weight_candidates = []
         for _, text, conf in results:
-            cleaned = text.lower().replace("kg", "").replace("kgs", "")
+            cleaned = text.lower()
+            cleaned = cleaned.replace("kg", "").replace("kgs", "")
             cleaned = cleaned.replace("o", "0").replace("O", "0")
             cleaned = cleaned.replace("s", "5").replace("S", "5")
             cleaned = cleaned.replace("g", "9").replace("G", "6")
             cleaned = re.sub(r"[^\d\.]", "", cleaned)
+
             if re.fullmatch(r"\d{2,4}(\.\d{1,2})?", cleaned):
                 weight_candidates.append((cleaned, conf))