Update utils/image_processor.py

utils/image_processor.py

@@ -5,46 +5,30 @@ from PIL import Image
 import torch
 from transformers import TrOCRProcessor, VisionEncoderDecoderModel
 
-# ✅ Load TrOCR model and processor once
+# ✅ Load TrOCR processor and model once
 try:
     processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
-    model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
-    model.eval()
+    trocr_model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
     print("✅ TrOCR model loaded.")
-    trocr_available = True
 except Exception as e:
-    print(f"❌ Failed to load TrOCR: {e}")
-    trocr_available = False
-
-def preprocess_image(image):
-    """
-    Preprocess image for OCR: convert to grayscale and enhance contrast.
-    """
-    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
-    denoised = cv2.fastNlMeansDenoising(gray, h=10)
-    processed = cv2.adaptiveThreshold(
-        denoised, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
-        cv2.THRESH_BINARY, 11, 2
-    )
-    return processed
+    print(f"❌ Failed to load TrOCR model: {e}")
+    processor = None
+    trocr_model = None
 
 def extract_text_from_image(image_path):
-    """
-    Extract handwritten text from an image using TrOCR
-    """
+    print(f"📂 Reading image from: {image_path}")
     try:
-        print(f"📂 Reading image from: {image_path}")  # ✅ log file path
+        if trocr_model is None or processor is None:
+            raise RuntimeError("TrOCR model or processor not loaded.")
 
         image = Image.open(image_path).convert("RGB")
         pixel_values = processor(images=image, return_tensors="pt").pixel_values
 
         generated_ids = trocr_model.generate(pixel_values)
-        text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0].strip()
-
-        print(f"📝 Extracted Text from {os.path.basename(image_path)}: {text}")  # ✅ PRINT EXTRACTED TEXT
+        generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
 
-        return text or "Text extraction failed."
+        return generated_text.strip() if generated_text else "Text extraction failed."
     
     except Exception as e:
-        print(f"❌ OCR failed on {image_path}: {str(e)}")
-        return "Text extraction failed."
+        print(f"❌ OCR failed on {image_path}: {e}")
+        return "Text extraction failed."