Spaces:
Runtime error
Runtime error
File size: 3,317 Bytes
e47538b 4c5b48d e47538b 747c9ad e47538b 747c9ad 1796d49 747c9ad e47538b cf6b359 4c5b48d c5a6d21 e47538b cf6b359 e47538b fe1f44f c5a6d21 fe1f44f c5a6d21 fe1f44f c5a6d21 fe1f44f c5a6d21 e47538b af6c9c5 250e824 b2a4c2e 747c9ad 0081600 99a4b22 56cdfa2 e47538b 6f7cb0d e47538b 99a4b22 e47538b |
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 |
import pandas as pd
import PIL
from PIL import Image
from PIL import ImageDraw
import gradio as gr
import torch
import easyocr
import omegaconf
import cv2
from vietocr.vietocr.tool.predictor import Predictor
from vietocr.vietocr.tool.config import Cfg
# Configure of VietOCR
config = Cfg.load_config_from_name('vgg_transformer')
# config = Cfg.load_config_from_file('vietocr/config.yml')
# config['weights'] = '/Users/bmd1905/Desktop/pretrain_ocr/vi00_vi01_transformer.pth'
config['cnn']['pretrained'] = True
config['predictor']['beamsearch'] = True
config['device'] = 'cpu' # mps
recognitor = Predictor(config)
def draw_boxes(image, bounds, color='yellow', width=2):
draw = ImageDraw.Draw(image)
for bound in bounds:
p0, p1, p2, p3 = bound[0]
draw.line([*p0, *p1, *p2, *p3, *p0], fill=color, width=width)
return image
def inference(filepath, lang):
img = cv2.imread(filepath)
width, height = img.size
reader = easyocr.Reader(lang)
bounds = reader.readtext(filepath)
new_bounds=[]
for (bbox, text, prob) in bounds:
(tl, tr, br, bl) = bbox
tl = (int(tl[0]), int(tl[1]))
tr = (int(tr[0]), int(tr[1]))
br = (int(br[0]), int(br[1]))
bl = (int(bl[0]), int(bl[1]))
min_x = min(tl[0], tr[0], br[0], bl[0])
min_x = max(0, min_x)
max_x = max(tl[0], tr[0], br[0], bl[0])
max_x = min(width-1, max_x)
min_y = min(tl[1], tr[1], br[1], bl[1])
min_y = max(0, min_y)
max_y = max(tl[1], tr[1], br[1], bl[1])
max_y = min(height-1, max_y)
# crop the region of interest (ROI)
cropped_image = img[min_y:max_y,min_x:max_x] # crop the image
cropped_image = Image.fromarray(cropped_image)
out = recognitor.predict(cropped_image)
print(out)
new_bounds.append((bbox,text, out, prob))
im = PIL.Image.open(filepath)
draw_boxes(im, bounds)
im.save('result.jpg')
return ['result.jpg', pd.DataFrame(new_bounds).iloc[: , 2:]]
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>"
examples = [['english.png',['en']],['thai.jpg',['th']],['french.jpg',['fr', 'en']],['chinese.jpg',['ch_sim', 'en']],['japanese.jpg',['ja', 'en']],['korean.png',['ko', 'en']],['Hindi.jpeg',['hi', 'en']]]
css = ".output_image, .input_image {height: 40rem !important; width: 100% !important;}"
choices = [
"vi"
]
gr.Interface(
inference,
[gr.inputs.Image(type='filepath', label='Input'),gr.inputs.CheckboxGroup(choices, type="value", default=['vi'], label='language')],
[gr.outputs.Image(type='pil', label='Output'), gr.outputs.Dataframe(type='pandas', headers=['easyOCR','vietOCR', 'confidence'])],
title=title,
description=description,
article=article,
css=css,
enable_queue=True
).launch(debug=True) |