app.py

# import gradio as gr
# from transformers import pipeline
from PIL import Image
import pytesseract
import easyocr
import cv2
import os

# pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")

# def predict(input_img):
#     predictions = pipeline(input_img)
#     return input_img, {p["label"]: p["score"] for p in predictions} 

# def recognize(input_img):
#     text = pytesseract.image_to_string(Image.open("./data/" + filename))
#     return input_img, text

# gradio_app = gr.Interface(
#     recognize,
#     inputs=[gr.Image(label="Upload an Image", type="pil")],
#     outputs=[gr.Textbox(label="Text in the Image")],
    
#     title="Extrate Text From Image",
# )

# if __name__ == "__main__":
#     gradio_app.launch(server_port=8756)


import os

import matplotlib.pyplot as plt
import streamlit as st 

import cv2
import tensorflow as tf
from PIL import Image
import pytesseract

DET_ARCHS = ["pytesseract", "easyocr"]

def main():

    # Wide mode
    st.set_page_config(layout="wide")

    # Designing the interface
    st.title("Image Text Recognition")
    # For newline
    st.write('\n')
    
    # Instructions
    st.markdown("*Hint: click on the top-right corner of an image to enlarge it!*")
    # Set the columns
    cols = st.columns((1, 1, 1, 1))
    cols[0].subheader("Input image")
    cols[1].subheader("OCR output")
    
    # Sidebar
    # File selection
    st.sidebar.title("Document selection")
    # Disabling warning
    # st.set_option('deprecation.showfileUploaderEncoding', False)
    # Choose your own image
    uploaded_file = st.sidebar.file_uploader("Upload files", type=['png', 'jpeg', 'jpg'])
    if uploaded_file is not None:
        doc = uploaded_file.read()
        cols[0].image(doc)

    # Model selection
    st.sidebar.title("Model selection")
    det_arch = st.sidebar.selectbox("OCR model", DET_ARCHS)

    # For newline
    st.sidebar.write('\n')

    if st.sidebar.button("Analyze image"):

        if uploaded_file is None:
            st.sidebar.write("Please upload a document")

        else:
            with st.spinner('Loading model...'):
                if det_arch == 'pytesseract':
                    predictor = pytesseract.image_to_string(Image.open(doc))
                else:
                    reader = easyocr.Reader(['en'])
                    predictor = reader.readtext("./data/" + filename, detail = 0)
            with st.spinner('Analyzing...'):

                # Plot OCR output
                if det_arch == 'pytesseract':
                    cols[1].text(predictor)
                else:
                    cols[1].text(''.join(text))

                
if __name__ == '__main__':
    main()