Update app.py

app.py

@@ -1,47 +1,46 @@
 from transformers import LayoutLMForTokenClassification, LayoutLMTokenizer
 import gradio as gr
 import cv2
-import torch
+import easyocr
+
+# Initialize EasyOCR reader for text extraction
+reader = easyocr.Reader(['en'])
 
 # Load pre-trained LayoutLM model and tokenizer
 model = LayoutLMForTokenClassification.from_pretrained("microsoft/layoutlm-large-uncased")
 tokenizer = LayoutLMTokenizer.from_pretrained("microsoft/layoutlm-large-uncased")
 
-# Function to extract text using LayoutLM
+# Function to extract text using EasyOCR and process with LayoutLM
 def extract_patient_info(image):
     # Convert the uploaded image to RGB (required by LayoutLM)
     image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
-    
-    # Here you can add code to process the image for LayoutLM (like extracting features)
-    # Since LayoutLM works better with structured documents, we can return simple OCR text 
-    # for demonstration purposes:
-    
-    # Tokenize and process the image text (you can customize the process depending on your image)
-    inputs = tokenizer(image_rgb, return_tensors="pt")
+
+    # Use EasyOCR to extract text from the image
+    result = reader.readtext(image_rgb)
+    extracted_text = " ".join([detection[1] for detection in result])
+
+    # Tokenize the extracted text with LayoutLM
+    inputs = tokenizer(extracted_text, return_tensors="pt")
     outputs = model(**inputs)
-    
-    # For demonstration purposes, we return some dummy output
-    # You can adjust this based on your image and use case (extract more meaningful text)
-    return "Extracted text using LayoutLM will go here."
+
+    # For this example, we return the extracted text (you can further process LayoutLM's output)
+    return extracted_text
 
 # Gradio interface setup
 with gr.Blocks() as demo:
-    gr.Markdown("### OCR Using LayoutLM Pretrained Model")
-    
+    gr.Markdown("### OCR Using LayoutLM Pretrained Model with EasyOCR")
+
     # Image upload component
     image_input = gr.Image(type="numpy", label="Upload Image")
-    
+
     # Output textboxes to display the extracted information
-    name_output = gr.Textbox(label="Patient Name")
-    age_output = gr.Textbox(label="Age")
-    gender_output = gr.Textbox(label="Gender")
-    phone_output = gr.Textbox(label="Phone Number")
-    
+    output_text = gr.Textbox(label="Extracted Text")
+
     # Button to trigger image processing and text extraction
     process_button = gr.Button("Process Image")
-    
+
     # When the button is clicked, process the image and show results in textboxes
-    process_button.click(fn=extract_patient_info, inputs=image_input, outputs=[name_output, age_output, gender_output, phone_output])
+    process_button.click(fn=extract_patient_info, inputs=image_input, outputs=output_text)
 
 # Launch the Gradio app
 if __name__ == "__main__":