Update ocr_engine.py

ocr_engine.py

@@ -1,43 +1,33 @@
-import easyocr
+from paddleocr import PaddleOCR
 import numpy as np
-import cv2
 import re
 
-reader = easyocr.Reader(['en'], gpu=False)
+ocr = PaddleOCR(use_angle_cls=True, lang='en', use_gpu=False)
 
 def extract_weight_from_image(pil_img):
     try:
         img = np.array(pil_img)
+        result = ocr.ocr(img, cls=True)
 
-        # 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)
-
-        results = reader.readtext(thresh)
-        all_texts = [text for _, text, _ in results]
-
+        all_text = []
         weight_candidates = []
-        for _, text, conf in results:
-            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))
+        for line in result:
+            for box, (text, confidence) in line:
+                all_text.append(text)
+                cleaned = text.lower()
+                cleaned = cleaned.replace("kg", "").replace("kgs", "")
+                cleaned = cleaned.replace("o", "0").replace("s", "5").replace("g", "9")
+                cleaned = re.sub(r"[^\d\.]", "", cleaned)
+
+                if re.fullmatch(r"\d{2,4}(\.\d{1,2})?", cleaned):
+                    weight_candidates.append((cleaned, confidence))
 
         if not weight_candidates:
-            return "Not detected", 0.0, "\n".join(all_texts)
+            return "Not detected", 0.0, "\n".join(all_text)
 
         best_weight, best_conf = sorted(weight_candidates, key=lambda x: -x[1])[0]
-        return best_weight, round(best_conf * 100, 2), "\n".join(all_texts)
+        return best_weight, round(best_conf * 100, 2), "\n".join(all_text)
 
     except Exception as e:
         return f"Error: {str(e)}", 0.0, "OCR failed"