File size: 3,690 Bytes
1569310
 
 
3c57165
1569310
 
3878fb6
1569310
2d7b88a
c82795d
697613a
1569310
 
 
93fe459
9e79a73
1569310
 
81f2edf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1569310
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b613d69
 
c0ff73d
b613d69
 
 
 
81f2edf
 
 
c8cfd54
b613d69
 
 
ecdecda
b613d69
1569310
b613d69
 
 
 
 
 
 
 
 
 
 
 
1569310
b613d69
 
1569310
 
 
 
b613d69
1569310
 
8439022
b613d69
 
 
1569310
b613d69
1ae8ebd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
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)