Spaces:
Running
Running
File size: 1,641 Bytes
b9e018b e871a21 b9e018b e871a21 b9e018b e871a21 b9e018b |
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 |
from PIL import Image
import pytesseract
import gradio as gr
import os
langs = []
choices = os.popen('tesseract --list-langs').read().split('\n')[1:-1]
blocks = gr.Blocks()
# If you don't have tesseract executable in your PATH, include the following:
# pytesseract.pytesseract.tesseract_cmd = r'<full_path_to_your_tesseract_executable>'
# Example tesseract_cmd = r'C:\Program Files (x86)\Tesseract-OCR\tesseract'
# Simple image to string
# print(pytesseract.image_to_string(Image.open('eurotext.png')))
# # French text image to string
# print(pytesseract.image_to_string(Image.open('test-european.jpg'), lang='fra'))
# # Get bounding box estimates
# print(pytesseract.image_to_boxes(Image.open('test.png')))
# # Get verbose data including boxes, confidences, line and page numbers
# print(pytesseract.image_to_data(Image.open('test.png')))
# # Get information about orientation and script detection
# print(pytesseract.image_to_osd(Image.open('test.png'))
def run(image, lang=None):
result = pytesseract.image_to_string(
image, lang=None if lang == [] else lang)
return result
with gr.Blocks() as demo:
gr.Markdown("## Hello pytesseract!")
with gr.Row():
with gr.Column():
image_in = gr.Image(type="pil")
lang = gr.Dropdown(choices)
btn = gr.Button("Run")
with gr.Column():
text_out = gr.TextArea()
examples = gr.Examples([["./eurotext.png", None]], fn=run, inputs=[
image_in, lang], outputs=[text_out], cache_examples=False)
btn.click(fn=run, inputs=[image_in, lang], outputs=[text_out])
demo.launch()
|