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 doctr.io import DocumentFile | |
| from doctr.models import ocr_predictor | |
| ocr_model = ocr_predictor(pretrained=True) | |
| """ | |
| Perform OCR with doctr | |
| """ | |
| def ocr_with_doctr(file): | |
| text_output = '' | |
| # Load the document | |
| doc = DocumentFile.from_pdf(file) | |
| # Perform OCR | |
| result = ocr_model(doc) | |
| # Extract text from OCR result | |
| for page in result.pages: | |
| for block in page.blocks: | |
| for line in block.lines: | |
| text_output += " ".join([word.value for word in line.words]) + "\n" | |
| return text_output | |
| """ | |
| Paddle OCR | |
| """ | |
| def ocr_with_paddle(img): | |
| finaltext = '' | |
| ocr = PaddleOCR(lang='en', use_angle_cls=True) | |
| # img_path = 'exp.jpeg' | |
| 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 | |
| """ | |
| # gray scale 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 | |
| def generate_ocr(Method, file): | |
| text_output = '' | |
| if isinstance(file, bytes): # Handle file uploaded as bytes | |
| file = io.BytesIO(file) | |
| if file.name.endswith('.pdf'): | |
| # Perform OCR on the PDF using doctr | |
| text_output = ocr_with_doctr(file) | |
| else: | |
| # Handle image file | |
| img_np = np.array(Image.open(file)) | |
| text_output = generate_text_from_image(Method, img_np) | |
| return text_output | |
| def generate_text_from_image(Method, img): | |
| text_output = '' | |
| if Method == 'EasyOCR': | |
| text_output = ocr_with_easy(img) | |
| elif Method == 'KerasOCR': | |
| text_output = ocr_with_keras(img) | |
| elif Method == 'PaddleOCR': | |
| text_output = ocr_with_paddle(img) | |
| return text_output | |
| import gradio as gr | |
| image_or_pdf = gr.File(label="Upload an image or PDF") | |
| method = gr.Radio(["PaddleOCR", "EasyOCR", "KerasOCR"], value="PaddleOCR") | |
| output = gr.Textbox(label="Output") | |
| demo = gr.Interface( | |
| generate_ocr, | |
| [method, image_or_pdf], | |
| output, | |
| title="Optical Character Recognition", | |
| 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(show_error=True) | |