Update ocr_engine.py

ocr_engine.py

@@ -3,20 +3,21 @@ from PIL import Image
 import torch
 import re
 
-# Load TrOCR model and processor once
+# Load TrOCR model and processor
 processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
 model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
 
 def extract_weight(image):
     try:
-        # OCR Inference
+        # Step 1: OCR with TrOCR
         pixel_values = processor(images=image, return_tensors="pt").pixel_values
         generated_ids = model.generate(pixel_values)
         text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0].strip()
         print("OCR Output:", text)
 
-        # Pattern to detect weight with optional decimal and unit (g or kg)
-        match = re.search(r'(\d{1,5}(?:\.\d{1,3})?)\s*(kg|g)', text.lower())
+        # Step 2: Search for weight pattern (g or kg)
+        pattern = r'(\d{1,5}(?:\.\d{1,3})?)\s*(kg|g)'  # e.g., 75.25 g, 98.78kg
+        match = re.search(pattern, text.lower())
 
         if match:
             value = match.group(1)