|
|
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 |
|
|
|
|
|
""" |
|
|
Paddle OCR |
|
|
""" |
|
|
def ocr_with_paddle(img): |
|
|
finaltext = '' |
|
|
ocr = PaddleOCR(lang='en') |
|
|
result_en = ocr.ocr(img) |
|
|
|
|
|
ocr_vi = PaddleOCR(lang='vi') |
|
|
result_vi = ocr_vi.ocr(img) |
|
|
|
|
|
def extract_text(result): |
|
|
return ' '.join([line[1][0] for line in result[0]]) |
|
|
|
|
|
en_text = extract_text(result_en) |
|
|
vi_text = extract_text(result_vi) |
|
|
|
|
|
finaltext = f"[EN]: {en_text}\n[VI]: {vi_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) |
|
|
for text, box in predictions[0]: |
|
|
output_text += ' ' + text |
|
|
return "[Detected]: " + output_text |
|
|
|
|
|
""" |
|
|
easy OCR |
|
|
""" |
|
|
|
|
|
def get_grayscale(image): |
|
|
return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) |
|
|
|
|
|
|
|
|
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(['vi', 'en']) |
|
|
bounds = reader.readtext('image.png', paragraph=False, detail=0) |
|
|
result_text = '\n'.join(bounds) |
|
|
return result_text |
|
|
|
|
|
""" |
|
|
Generate OCR |
|
|
""" |
|
|
def generate_ocr(Method, img): |
|
|
if img is None or not (img).any(): |
|
|
raise gr.Error("Please upload an image!") |
|
|
|
|
|
text_output = '' |
|
|
print("Method selected:", Method) |
|
|
|
|
|
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) |
|
|
|
|
|
try: |
|
|
flag(Method, text_output, img) |
|
|
except Exception as e: |
|
|
print("Flag error:", e) |
|
|
|
|
|
return text_output |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
""" |
|
|
Create user interface for OCR demo |
|
|
""" |
|
|
|
|
|
|
|
|
image = gr.Image() |
|
|
method = gr.Radio(["PaddleOCR","EasyOCR", "KerasOCR"],value="PaddleOCR") |
|
|
output = gr.Textbox(label="Output") |
|
|
|
|
|
demo = gr.Interface( |
|
|
generate_ocr, |
|
|
[method,image], |
|
|
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:letstalk@pragnakalp.com" target="_blank">letstalk@pragnakalp.com</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) |
|
|
|
