Spaces:
Sleeping
Sleeping
File size: 1,697 Bytes
ac510cd |
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 |
from detectron2.data.detection_utils import read_image,pil_image_to_numpy
from detectron2.utils.visualizer import Visualizer
from sam_everything import visimage_to_pil
import numpy as np
def do_ocr(ocr_type,input):
print(ocr_type)
result = None
np_image = pil_image_to_numpy(input)
if ocr_type == "OCR":
from paddleocr import PaddleOCR
ocr = PaddleOCR(lang='ch', use_angle_cls=True)
# img_path = 'exp.jpeg'
result = ocr.ocr(np_image)
print(result)
result = parse_paddle_result(result)
elif ocr_type == "Easy":
import easyocr
reader = easyocr.Reader(['en','ch_sim']) # 初始化 EasyOCR，选择需要支持的语言（例如英文）
result = reader.readtext(np_image)
result = parse_esay_result(result)
view = Visualizer(np_image)
for item in result:
polygon = np.array(item['box'])
view.draw_polygon(polygon, "k")
vis_image = view.get_output()
pil_images = visimage_to_pil([vis_image])
return pil_images[0],result
def parse_esay_result(data):
results = []
for entry in data:
box = entry[0]
text = entry[1]
confidence = entry[2]
result = {
'box': box,
'text': text,
'confidence': confidence
}
results.append(result)
return results
def parse_paddle_result(data):
results = []
for entry in data[0]:
box = entry[0]
text = entry[1][0]
confidence = entry[1][1]
result = {
'box': box,
'text': text,
'confidence': confidence
}
results.append(result)
return results
|