Tesseract-OCR / app_interface.py
kneelesh48's picture
Add application file
2509048
raw
history blame
1.19 kB
from typing import List
import pytesseract
from PIL import Image
import gradio as gr
def tesseract_ocr(filepath: str, languages: List[str]):
image = Image.open(filepath)
return pytesseract.image_to_string(image=image, lang=', '.join(languages))
title = "Tesseract OCR"
description = "Gradio demo for Tesseract. Tesseract is an open source text recognition (OCR) Engine."
article = "<p style='text-align: center'><a href='https://tesseract-ocr.github.io/' target='_blank'>Tesseract documentation</a> | <a href='https://github.com/tesseract-ocr/tesseract' target='_blank'>Github Repo</a></p>"
examples = [
['examples/eurotext.png', ['eng']],
['examples/tesseract_sample.png', ['jpn', 'eng']],
['examples/chi.jpg', ['HanS', 'HanT']]
]
language_choices = pytesseract.get_languages()
demo = gr.Interface(
fn=tesseract_ocr,
inputs=[
gr.Image(type="filepath", label="Input"),
gr.CheckboxGroup(language_choices, type="value", value=['eng'], label='language')
],
outputs='text',
title=title,
description=description,
article=article,
examples=examples,
)
if __name__ == '__main__':
demo.launch()