Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import pytesseract | |
| from PIL import Image | |
| import pdf2image | |
| import tempfile | |
| import os | |
| import cv2 | |
| import numpy as np | |
| # You may need to set the path to tesseract executable if it's not in PATH | |
| # pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe' # For Windows | |
| # For Linux/Mac, ensure Tesseract is installed | |
| def preprocess_image(img): | |
| """Preprocess image to improve OCR accuracy for handwritten text""" | |
| # Convert to grayscale | |
| img_array = np.array(img) | |
| # Check if the image is already grayscale | |
| if len(img_array.shape) == 2: | |
| gray = img_array | |
| else: | |
| gray = cv2.cvtColor(img_array, cv2.COLOR_RGB2GRAY) | |
| # Apply thresholding | |
| _, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU) | |
| # Noise removal | |
| kernel = np.ones((1, 1), np.uint8) | |
| binary = cv2.morphologyEx(binary, cv2.MORPH_CLOSE, kernel) | |
| binary = cv2.morphologyEx(binary, cv2.MORPH_OPEN, kernel) | |
| # Invert back | |
| binary = 255 - binary | |
| return Image.fromarray(binary) | |
| def extract_text_from_image(img): | |
| """Extract text from an image using OCR""" | |
| # Preprocess for better handwriting recognition | |
| processed_img = preprocess_image(img) | |
| # Use pytesseract with configuration optimized for handwritten text | |
| custom_config = r'--oem 3 --psm 6 -l eng -c tessedit_char_whitelist="ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789.,!?@#$%^&*()-+=_:;\'\" "' | |
| text = pytesseract.image_to_string(processed_img, config=custom_config) | |
| return text.strip() | |
| def extract_text_from_pdf(pdf_path): | |
| """Extract text from all pages of a PDF file""" | |
| # Convert PDF to images | |
| with tempfile.TemporaryDirectory() as path: | |
| images = pdf2image.convert_from_path(pdf_path, output_folder=path) | |
| # Extract text from each page | |
| full_text = [] | |
| for img in images: | |
| text = extract_text_from_image(img) | |
| full_text.append(text) | |
| return "\n\n--- Page Break ---\n\n".join(full_text) | |
| def process_file(file): | |
| """Process the uploaded file (PDF or image)""" | |
| if file is None: | |
| return "No file uploaded. Please upload an image or PDF file." | |
| file_extension = os.path.splitext(file.name)[1].lower() | |
| if file_extension == ".pdf": | |
| # Process PDF | |
| return extract_text_from_pdf(file.name) | |
| elif file_extension in [".jpg", ".jpeg", ".png", ".bmp", ".tiff", ".tif"]: | |
| # Process Image | |
| img = Image.open(file.name) | |
| return extract_text_from_image(img) | |
| else: | |
| return "Unsupported file format. Please upload a PDF or image file (JPG, PNG, BMP, TIFF)." | |
| # Create Gradio interface | |
| with gr.Blocks(title="Handwritten Text OCR Extractor") as app: | |
| gr.Markdown("# Handwritten Text OCR Extraction Tool") | |
| gr.Markdown("Upload an image or PDF containing handwritten text to extract the content.") | |
| with gr.Row(): | |
| with gr.Column(): | |
| file_input = gr.File(label="Upload Image or PDF") | |
| extract_button = gr.Button("Extract Text") | |
| with gr.Column(): | |
| text_output = gr.Textbox(label="Extracted Text", lines=10, placeholder="Extracted text will appear here...") | |
| extract_button.click(fn=process_file, inputs=[file_input], outputs=[text_output]) | |
| gr.Markdown("### Notes:") | |
| gr.Markdown("- For best results, ensure the handwriting is clear and the image is well-lit") | |
| gr.Markdown("- The system works best with dark text on light background") | |
| gr.Markdown("- Multiple page PDFs will show page breaks in the output") | |
| # Launch the app | |
| if __name__ == "__main__": | |
| app.launch() |