PaddleOCR使用笔记

Linux环境下

paddleocr package使用说明

Windows下使用

安装whl包

pip安装

pip install "paddleocr>=2.0.1" # 推荐使用2.0.1+版本

代码使用

• 检测+分类+识别全流程

from paddleocr import PaddleOCR
from tools.infer.utility import draw_ocr
# Paddleocr目前支持中英文、英文、法语、德语、韩语、日语，可以通过修改lang参数进行切换
# 参数依次为`ch`, `en`, `french`, `german`, `korean`, `japan`。
ocr = PaddleOCR(use_angle_cls=True, use_gpu=False, lang="ch") # need to run only once to download and load model into memory
img_path = './doc/imgs/11.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='/path/to/PaddleOCR/doc/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('./results/det_cls_rec_result.jpg')

• 检测+识别

from paddleocr import PaddleOCR
from tools.infer.utility import draw_ocr
ocr = PaddleOCR(use_gpu=False) # need to run only once to download and load model into memory
img_path = './doc/imgs/11.jpg'
result = ocr.ocr(img_path)
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='/path/to/PaddleOCR/doc/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('./results/det_rec_result.jpg')

• 分类+识别

from paddleocr import PaddleOCR
ocr = PaddleOCR(use_gpu=False, use_angle_cls=True) # need to run only once to download and load model into memory
img_path = './doc/imgs_words/ch/word_1.jpg'
result = ocr.ocr(img_path, det=False, cls=True)
for line in result:
    print(line)

结果是一个list，每个item只包含识别结果和识别置信度

('韩国小馆', 0.9972204)

• 单独执行检测

from paddleocr import PaddleOCR
from tools.infer.utility import draw_ocr
ocr = PaddleOCR(use_gpu=False) # need to run only once to download and load model into memory
img_path = './doc/imgs/11.jpg'
result = ocr.ocr(img_path, rec=False)
for line in result:
    print(line)

# 显示结果
from PIL import Image

image = Image.open(img_path).convert('RGB')
im_show = draw_ocr(image, result, txts=None, scores=None, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('./results/det_result.jpg')

• 单独执行识别

from paddleocr import PaddleOCR
ocr = PaddleOCR(use_gpu=False) # need to run only once to download and load model into memory
img_path = './doc/imgs_words/ch/word_1.jpg'
result = ocr.ocr(img_path, det=False)
for line in result:
    print(line)

结果是一个list，每个item只包含识别结果和识别置信度

('韩国小馆', 0.9972204)

• 单独执行分类

from paddleocr import PaddleOCR
ocr = PaddleOCR(use_gpu=False, use_angle_cls=True) # need to run only once to download and load model into memory
img_path = './doc/imgs_words/ch/word_1.jpg'
result = ocr.ocr(img_path, det=False, rec=False, cls=True)
for line in result:
    print(line)

结果是一个list，每个item只包含分类结果和分类置信度

['0', 0.9998784]

自定义模型

from paddleocr import PaddleOCR
from tools.infer.utility import draw_ocr
# The path of detection and recognition model must contain model and params files
ocr = PaddleOCR(use_gpu=False, det_model_dir='./inference/ch_det_mv3_db/', rec_model_dir='./inference/rec_en_number_lite/', rec_char_dict_path='./ppocr/utils/dict/en_dict.txt')
img_path = './doc/imgs_10_BZ_test/20160517_100146_H4H2930367BZ_Z.jpg'
result = ocr.ocr(img_path, cls=True)
for line in result:
    print(line)

# draw result
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='/path/to/PaddleOCR/doc/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('./results/custom_result.jpg')

Linux下命令行使用

安装whl包

pip3 install "paddleocr>=2.0.1" -i https://pypi.tuna.tsinghua.edu.cn/simple

• 查看帮助信息

paddleocr -h

使用自定义模型

• ~~要换一个目录，~~还要用pip3.8

pip3.8 install "paddleocr>=2.0.1"

• 不用换目录，但要改paddleocr.py的代码：

- SUPPORT_DET_MODEL = ['DB']
+ SUPPORT_DET_MODEL = ['DB', 'EAST']

• 使用自定义模型

from paddleocr import PaddleOCR
from tools.infer.utility import draw_ocr
# The path of detection and recognition model must contain model and params files
ocr = PaddleOCR(det_model_dir='./inference/det_mv3_east/', rec_model_dir='./inference/rec_en_number_lite_crown/', use_space_char=False, rec_char_type='EN', det_algorithm='EAST', rec_char_dict_path='ppocr/utils/dict/en_dict.txt')
img_path = './doc/imgs_crown_test/20160517_101050_A8Y0930108BZ_Z.jpg'
result = ocr.ocr(img_path)
for line in result:
    print(line)

# draw result
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='./doc/fonts/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('./results/det_rec_20160517_101050_A8Y0930108BZ_Z.jpg')

创作不易，喜欢的话加个关注点个赞，❤谢谢谢谢❤