File size: 2,813 Bytes
334adc2
 
9668774
334adc2
9668774
 
334adc2
b775b9c
0851882
 
1aa5d0c
9bccd26
0851882
 
 
 
334adc2
0851882
 
3664fda
 
97cd054
0851882
 
 
 
 
 
 
 
 
 
 
 
97cd054
0851882
 
97cd054
 
0851882
9668774
644d5b5
f4de4aa
644d5b5
f4de4aa
644d5b5
f4de4aa
20e28ec
c5c4e79
334adc2
 
 
 
0851882
ba29956
334adc2
 
9668774
334adc2
 
 
9668774
c5c4e79
334adc2
20e28ec
 
 
f4de4aa
334adc2
9668774
 
c5c4e79
334adc2
9668774
 
 
6ad9946
9668774
 
 
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
import pandas as pd
import PIL
from PIL import Image
from PIL import ImageDraw
import gradio as gr
import torch
import easyocr
import cv2
import math
import numpy as np

torch.hub.download_url_to_file('https://i.pinimg.com/originals/45/d0/30/45d03054e15f4be731781eecba7458a4.jpg', 'korean.png')
def midpoint(x1, y1, x2, y2):
    x_mid = int((x1 + x2)/2)
    y_mid = int((y1 + y2)/2)
    return (x_mid, y_mid)

def draw_boxes(img, bounds, color='yellow', width=2):
    draw = ImageDraw.Draw(img)
    for bound in bounds:
        p0, p1, p2, p3 = bound[0]
        """
        #for masking the image
        x0, y0 = p0[0][1]
        x1, y1 = p1[0][1]
        x2, y2 = p2[0][1]
        x3, y3 = p3[0][1]
        x_mid0, y_mid0 = midpoint(x1, y1, x2, y2)
        x_mid1, y_mi1 = midpoint(x0, y0, x3, y3)
        thickness = int(math.sqrt( (x2 - x1)**2 + (y2 - y1)**2))
        
        mask = np.zeros(img.shape[:2], dtype="uint8")
        cv2.line(mask, (x_mid0, y_mid0), (x_mid1, y_mi1), 255, thickness)
        masked = cv2.bitwise_and(img, img, mask=mask)
        """
        
        
        draw.line([*p0, *p1, *p2, *p3, *p0], fill=color, width=width)
    return img
        
def inference(img, lang):
    if lang == "english":
        lang = ['en']
    elif lang == "chinese":
        lang = ['ch_sim']
    elif lang == "korean":
        lang = ['ko']
    else:
        lang = ['ja']
    reader = easyocr.Reader(lang)
    bounds = reader.readtext(img.name)
    im = PIL.Image.open(img.name)
    draw_boxes(im, bounds)
    #remove_text(im, bounds)
    lang = ""
    im.save('result.jpg')
    return ['result.jpg', pd.DataFrame(bounds).iloc[: , 1:]]

title = 'EasyOCR'
description = 'Gradio demo for EasyOCR. EasyOCR demo supports 80+ languages.To use it, simply upload your image and choose a language from the dropdown menu, or click one of the examples to load them. Read more at the links below.'
article = "<p style='text-align: center'><a href='https://www.jaided.ai/easyocr/'>Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.</a> | <a href='https://github.com/JaidedAI/EasyOCR'>Github Repo</a></p>"
css = ".output_image, .input_image {height: 40rem !important; width: 100% !important;}"
examples = [['korean.png',"korean"]]
choices = [
    "chinese",
    "english",
    "japanese",
    "korean"
]
gr.Interface(
    inference,
    [gr.inputs.Image(type='file', label='Input'),gr.inputs.Dropdown(choices, type="value", default="korean", label='language')],
    [gr.outputs.Image(type='file', label='Output'), gr.outputs.Dataframe(headers=['text', 'confidence'])],
    title=title,
    description=description,
    article=article,
    examples=examples,
    css=css,
    enable_queue=True
    ).launch(debug=True)