app.py

import streamlit as st
import easyocr
from PIL import Image
import re

# Initialize EasyOCR Reader
reader = easyocr.Reader(['en', 'hi'])

# Streamlit app title
st.title("Image Text Extraction and Keyword Search using EasyOCR")

# File uploader for image input
uploaded_image = st.file_uploader("Upload an image", type=['png', 'jpg', 'jpeg'])

if uploaded_image is not None:
    # Load the uploaded image
    image = Image.open(uploaded_image)
    
    # Display the image
    st.image(image, caption='Uploaded Image', use_column_width=True)
    
    # Perform OCR
    with st.spinner("Extracting text..."):
        results = reader.readtext(image)
    
    # Extract the text
    extracted_text = " ".join([text for (_, text, _) in results])
    
    if extracted_text:
        st.success("Extracted Text:")
        st.write(extracted_text)

        # Keyword search feature
        keyword = st.text_input("Enter a keyword to search in the extracted text:")

        if keyword:
            # Highlight matches
            highlighted_text = re.sub(f"({keyword})", r"<mark>\1</mark>", extracted_text, flags=re.IGNORECASE)
            st.markdown(f"**Search Results for '{keyword}':**", unsafe_allow_html=True)
            st.markdown(highlighted_text, unsafe_allow_html=True)
        else:
            st.info("Enter a keyword to search.")
    else:
        st.warning("No text detected in the image.")