Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import tensorflow as tf | |
| import keras_ocr | |
| import requests | |
| import cv2 | |
| import os | |
| import csv | |
| import numpy as np | |
| import pandas as pd | |
| import huggingface_hub | |
| from huggingface_hub import Repository | |
| from datetime import datetime | |
| import scipy.ndimage.interpolation as inter | |
| import easyocr | |
| import datasets | |
| from datasets import load_dataset, Image | |
| from PIL import Image | |
| from paddleocr import PaddleOCR | |
| from save_data import flag | |
| from transformers import pipeline # Importing the pipeline | |
| """ | |
| Paddle OCR | |
| """ | |
| def ocr_with_paddle(img): | |
| finaltext = '' | |
| ocr = PaddleOCR(lang='en', use_angle_cls=True) | |
| result = ocr.ocr(img) | |
| for i in range(len(result[0])): | |
| text = result[0][i][1][0] | |
| finaltext += ' ' + text | |
| return finaltext | |
| """ | |
| Keras OCR | |
| """ | |
| def ocr_with_keras(img): | |
| output_text = '' | |
| pipeline = keras_ocr.pipeline.Pipeline() | |
| images = [keras_ocr.tools.read(img)] | |
| predictions = pipeline.recognize(images) | |
| first = predictions[0] | |
| for text, box in first: | |
| output_text += ' ' + text | |
| return output_text | |
| """ | |
| easy OCR | |
| """ | |
| # grayscale image | |
| def get_grayscale(image): | |
| return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) | |
| # Thresholding or Binarization | |
| def thresholding(src): | |
| return cv2.threshold(src, 127, 255, cv2.THRESH_TOZERO)[1] | |
| def ocr_with_easy(img): | |
| gray_scale_image = get_grayscale(img) | |
| thresholding(gray_scale_image) | |
| cv2.imwrite('image.png', gray_scale_image) | |
| reader = easyocr.Reader(['th', 'en']) | |
| bounds = reader.readtext('image.png', paragraph="False", detail=0) | |
| bounds = ''.join(bounds) | |
| return bounds | |
| """ | |
| Generate OCR | |
| """ | |
| def generate_ocr(Method, img): | |
| text_output = '' | |
| if (img).any(): | |
| print("Method___________________", Method) | |
| if Method == 'EasyOCR': | |
| text_output = ocr_with_easy(img) | |
| if Method == 'KerasOCR': | |
| text_output = ocr_with_keras(img) | |
| if Method == 'PaddleOCR': | |
| text_output = ocr_with_paddle(img) | |
| try: | |
| flag(Method, text_output, img) | |
| except Exception as e: | |
| print(e) | |
| # Generate Text using FLAN-T5 model | |
| text_gen = generate_text_with_flan_t5(text_output) | |
| return text_gen | |
| else: | |
| raise gr.Error("Please upload an image!!!!") | |
| """ | |
| Text Generation using FLAN-T5 | |
| """ | |
| def generate_text_with_flan_t5(input_text): | |
| # Load the pre-trained FLAN-T5 model | |
| pipe = pipeline("text2text-generation", model="google/flan-t5-large") | |
| # Use the model to generate a response based on the OCR output | |
| output = pipe(input_text) | |
| return output[0]['generated_text'] | |
| """ | |
| Create user interface for OCR demo | |
| """ | |
| image = gr.Image() | |
| method = gr.Radio(["PaddleOCR", "EasyOCR", "KerasOCR"], value="PaddleOCR") | |
| output = gr.Textbox(label="Generated Text") | |
| demo = gr.Interface( | |
| generate_ocr, | |
| [method, image], | |
| output, | |
| title="Optical Character Recognition and Text Generation", | |
| css=".gradio-container {background-color: lightgray} #radio_div {background-color: #FFD8B4; font-size: 40px;}", | |
| article="""<p style='text-align: center;'>Feel free to give us your thoughts on this demo and please contact us at | |
| <a href="mailto:[email protected]" target="_blank">[email protected]</a> | |
| <p style='text-align: center;'>Developed by: <a href="https://www.pragnakalp.com" target="_blank">Pragnakalp Techlabs</a></p>""" | |
| ) | |
| demo.launch() | |