使用Padddle v2.3识别下车牌

Criss · 发表于 2021-9-19 19:50:10

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 = 'C:/Users/Criss/Desktop/22.jpg'
result = ocr.ocr(img_path, cls=True)
for line in result:
print(line)
# 显示结果
from PIL import Image
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='./fonts/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')

复制代码

导入代码到pycharm中，然后运行即可。

识别效果：

[2021/09/19 19:47:30] root DEBUG: dt_boxes num : 4, elapse : 0.16655516624450684
[2021/09/19 19:47:30] root DEBUG: cls num : 4, elapse : 0.04388308525085449
[2021/09/19 19:47:31] root DEBUG: rec_res num : 4, elapse : 0.28022098541259766
[[[34.0, 137.0], [457.0, 134.0], [458.0, 229.0], [35.0, 233.0]], ('赣B·1D569', 0.9075086)]
[[[396.0, 345.0], [495.0, 345.0], [495.0, 365.0], [396.0, 365.0]], ('51halcon.com', 0.97081804)]

复制代码

不得不说，真6啊！

paddleocr中文使用说明：
https://github.com/PaddlePaddle/ ... oc_ch/quickstart.md

xuyongze · 发表于 2021-9-20 18:22:05

paddleocr收费吗、

Criss · 发表于 2021-9-21 07:54:58

xuyongze 发表于 2021-9-20 18:22
paddleocr收费吗、

百度开源的OCR深度识别框架