Update ocr_engine.py

ocr_engine.py

@@ -2,26 +2,29 @@ from transformers import TrOCRProcessor, VisionEncoderDecoderModel
 from PIL import Image, ImageEnhance
 import re
 
-# Load model trained for printed fonts (not handwriting)
+# ✅ Load model optimized for printed text (NOT handwritten)
 processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-printed")
 model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-printed")
 
 def extract_weight(image: Image.Image) -> str:
+    # Step 1: Preprocess image to enhance readability
     image = image.convert("L")  # grayscale
     image = ImageEnhance.Contrast(image).enhance(2.0)
     image = ImageEnhance.Sharpness(image).enhance(2.5)
     image = image.convert("RGB")
 
+    # Step 2: Run TrOCR
     pixel_values = processor(images=image, return_tensors="pt").pixel_values
     generated_ids = model.generate(pixel_values, max_length=32)
     full_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
-
     print("OCR Output:", full_text)
 
+    # Step 3: Extract numeric value
     cleaned = full_text.lower().replace(" ", "")
     match = re.search(r"(\d+(\.\d+)?)", cleaned)
     weight = match.group(1) if match else None
 
+    # Step 4: Determine unit
     if any(u in cleaned for u in ["kg", "kgs", "kilo"]):
         unit = "kg"
     elif any(u in cleaned for u in ["g", "gram", "grams"]):