Python Image OCR

参考链接

• 参考文章: https://github.com/PaddlePaddle/PaddleOCR
• 参考文章: https://blog.csdn.net/weixin_41258131/article/details/133163718?spm=1001.2101.3001.6650.2&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-2-133163718-blog-114925433.235%5Ev39%5Epc_relevant_anti_t3&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7ERate-2-133163718-blog-114925433.235%5Ev39%5Epc_relevant_anti_t3&utm_relevant_index=5

示例

from paddleocr import PaddleOCR, draw_ocr

# Paddleocr目前支持的多语言语种可以通过修改lang参数进行切换
# 例如`ch`, `en`, `fr`, `german`, `korean`, `japan`
ocr = PaddleOCR(use_angle_cls=True, lang="ch")  # need to run only once to download and load model into memory
img_path = './images/images_19.png'
result = ocr.ocr(img_path, cls=True)
for idx in range(len(result)):
    res = result[idx]
    for line in res:
        print(line)

# 显示结果
# 如果本地没有simfang.ttf，可以在doc/fonts目录下下载
from PIL import Image

result = result[0]
image = Image.open(img_path).convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
scores = [line[1][1] for line in result]
im_show = draw_ocr(image, boxes, txts, scores, font_path='doc/fonts/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')