File size: 1,515 Bytes
18d9ff0 4c247ff 4a935de 18d9ff0 b3d2248 18d9ff0 |
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 requests
import gradio as gr
import pandas as pd
from PIL import Image, ImageDraw
def infer(im):
im.save('converted.png')
url = 'https://ajax.thehive.ai/api/demo/classify?endpoint=text_recognition'
files = {
'image': ('converted.png', open('converted.png', 'rb'), 'image/png'),
'model_type': (None, 'detection'),
'media_type': (None, 'photo'),
}
headers = {
'referer': 'https://thehive.ai/'
}
r = requests.post(url, headers=headers, files=files)
res = r.json()
print(r, res)
img = im.convert('RGB')
words = []
draw = ImageDraw.Draw(img,'RGBA')
for output in res['response']['output']:
for poly in output['bounding_poly']:
words += [c['class'] for c in poly['classes']]
draw.rectangle((poly['dimensions']['left']-2,poly['dimensions']['top']-2,poly['dimensions']['right']+2,poly['dimensions']['bottom']+2), outline=(0,255,0,255), fill=(0,255,0,50),width=2)
img.save('result.png')
return 'result.png', '\n'.join([o['block_text'] for o in res['response']['output']]), pd.DataFrame(words)
iface = gr.Interface(
fn=infer,
title="Hive OCR",
description="Demo for Hive OCR.Transcribe and analyze media depicting typed, written, or graphic text",
inputs=[gr.inputs.Image(label='image', type='pil')],
outputs=['image', 'text', gr.outputs.Dataframe(headers=['word'])],
examples=['testocr.png', 'receipt.webp', '20131216170659.jpg'],
article="<a href=\"https://thehive.ai/hive-ocr-solutions\">Hive OCR</a>",
).launch() |