Spaces:
Sleeping
Sleeping
| # app.py | |
| import streamlit as st | |
| import cv2 | |
| import numpy as np | |
| import pytesseract | |
| from PIL import Image | |
| import re | |
| # Set the title of the webpage | |
| st.title("OCR Text Extraction Tool") | |
| # Uploading an image | |
| uploaded_file = st.file_uploader("Upload an Image", type=["jpg", "jpeg", "png"]) | |
| if uploaded_file is not None: | |
| # Convert the uploaded file content to an image | |
| image = Image.open(uploaded_file) | |
| # Convert PIL Image to OpenCV format | |
| opencv_image = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR) | |
| # Display the image | |
| st.image(image, caption='Uploaded Image', use_column_width=True) | |
| try: | |
| # Perform OCR | |
| text = pytesseract.image_to_string(opencv_image) | |
| st.subheader("Extracted Text:") | |
| st.write(text) | |
| # Search functionality | |
| search_keyword = st.text_input("Enter a keyword to search in the extracted text:") | |
| if search_keyword: | |
| pattern = re.compile(re.escape(search_keyword), re.IGNORECASE) | |
| matches = list(pattern.finditer(text)) | |
| if matches: | |
| st.markdown("### Keyword Found:") | |
| for match in matches: | |
| start, end = match.span() | |
| context_start = max(0, start - 50) | |
| context_end = min(len(text), end + 50) | |
| context = text[context_start:context_end] | |
| highlighted_text = ( | |
| context[:start-context_start] + | |
| f"<span style='background-color: yellow;'>{context[start-context_start:end-context_start]}</span>" + | |
| context[end-context_start:] | |
| ) | |
| st.markdown(f"...{highlighted_text}...") | |
| else: | |
| st.write(f"Keyword '{search_keyword}' not found in the extracted text.") | |
| except Exception as e: | |
| st.error(f"An error occurred while processing the image: {str(e)}") |