Update app.py

app.py

@@ -1,19 +1,34 @@
 import gradio as gr
 from transformers import pipeline
+from PIL import Image, ImageEnhance, ImageFilter
 
 # Load the OCR model
 ocr_model = pipeline("image-to-text", model="microsoft/trocr-large-printed")
 
-def recognize_text(image):
-    # Use the model on the input image
-    result = ocr_model(image)
-    return result[0]['generated_text']  # Return the recognized text
+def preprocess_image(image_path):
+    # Open the image
+    image = Image.open(image_path)
+    # Convert to grayscale
+    image = image.convert("L")
+    # Enhance the contrast
+    enhancer = ImageEnhance.Contrast(image)
+    image = enhancer.enhance(2)  # Adjust contrast level as needed
+    # Optionally apply a filter
+    image = image.filter(ImageFilter.SHARPEN)
+    return image
+
+def recognize_text(image_path):
+    # Preprocess the image
+    preprocessed_image = preprocess_image(image_path)
+    # Use the model on the preprocessed image
+    result = ocr_model(preprocessed_image)
+    return result[0]['generated_text']
 
 # Set up the Gradio interface
 interface = gr.Interface(
     fn=recognize_text,
     inputs=gr.Image(type="filepath"),  # Use filepath to accept image input
-    outputs="text",  # Output the recognized text
+    outputs="text",
     title="OCR with Trocr",
     description="Upload an image to recognize text using the Trocr model."
 )