File size: 1,524 Bytes
11cf59b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os
os.system('pip install paddlepaddle')
os.system('pip install paddleocr')
from paddleocr import PaddleOCR, draw_ocr
from PIL import Image
import gradio as gr
import torch

torch.hub.download_url_to_file('https://i.imgur.com/aqMBT0i.jpg', 'example.jpg')

def inference(img, lang):
    ocr = PaddleOCR(use_angle_cls=True, lang=lang,use_gpu=False)
    img_path = img.name
    result = ocr.ocr(img_path, cls=True)
    image = Image.open(img_path).convert('RGB')
    boxes = [line[0] for line in result]
    txts = [line[1][0] for line in result]
    # scores = [line[1][1] for line in result]
    im_show = draw_ocr(image, boxes, txts,
                       font_path='simfang.ttf')
    im_show = Image.fromarray(im_show)
    im_show.save('result.jpg')
    return 'result.jpg'

title = 'A Framework for Data-Driven Document Evaluation and scoring - Image to Text Extraction '
description = 'Demo for Optical character recognition(OCR) Using Tesseract and openCV for Mtech Project'
article = ""
examples = [['example.jpg','en']]
css = ".output_image, .input_image {height: 40rem !important; width: 100% !important;}"
gr.Interface(
    inference,
    [gr.inputs.Image(type='file', label='Input'),gr.inputs.Dropdown(choices=['ch', 'en', 'fr', 'german', 'korean', 'japan'], type="value", default='en', label='language')],
    gr.outputs.Image(type='file', label='Output'),
    title=title,
    description=description,
    article=article,
    examples=examples,
    css=css,
    enable_queue=True
    ).launch(debug=True)