Paddleocr Package

1 Get started quickly

1.1 install package

install by pypi

pip install "paddleocr>=2.0.1" # Recommend to use version 2.0.1+

build own whl package and install

python3 setup.py bdist_wheel
pip3 install dist/paddleocr-x.x.x-py3-none-any.whl # x.x.x is the version of paddleocr

2 Use

2.1 Use by code

The paddleocr whl package will automatically download the ppocr lightweight model as the default model, which can be customized and replaced according to the section 3 Custom Model.

• detection angle classification and recognition

from paddleocr import PaddleOCR,draw_ocr
# Paddleocr supports Chinese, English, French, German, Korean and Japanese.
# You can set the parameter `lang` as `ch`, `en`, `french`, `german`, `korean`, `japan`
# to switch the language model in order.
ocr = PaddleOCR(use_angle_cls=True, lang='en') # need to run only once to download and load model into memory
img_path = 'PaddleOCR/doc/imgs_en/img_12.jpg'
result = ocr.ocr(img_path, cls=True)
for idx in range(len(result)):
    res = result[idx]
    for line in res:
        print(line)

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

Output will be a list, each item contains bounding box, text and recognition confidence

[[[442.0, 173.0], [1169.0, 173.0], [1169.0, 225.0], [442.0, 225.0]], ['ACKNOWLEDGEMENTS', 0.99283075]]
[[[393.0, 340.0], [1207.0, 342.0], [1207.0, 389.0], [393.0, 387.0]], ['We would like to thank all the designers and', 0.9357758]]
[[[399.0, 398.0], [1204.0, 398.0], [1204.0, 433.0], [399.0, 433.0]], ['contributors whohave been involved in the', 0.9592447]]
......

Visualization of results

• detection and recognition

from paddleocr import PaddleOCR,draw_ocr
ocr = PaddleOCR(lang='en') # need to run only once to download and load model into memory
img_path = 'PaddleOCR/doc/imgs_en/img_12.jpg'
result = ocr.ocr(img_path, cls=False)
for idx in range(len(result)):
    res = result[idx]
    for line in res:
        print(line)

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

Output will be a list, each item contains bounding box, text and recognition confidence

[[[442.0, 173.0], [1169.0, 173.0], [1169.0, 225.0], [442.0, 225.0]], ['ACKNOWLEDGEMENTS', 0.99283075]]
[[[393.0, 340.0], [1207.0, 342.0], [1207.0, 389.0], [393.0, 387.0]], ['We would like to thank all the designers and', 0.9357758]]
[[[399.0, 398.0], [1204.0, 398.0], [1204.0, 433.0], [399.0, 433.0]], ['contributors whohave been involved in the', 0.9592447]]
......

Visualization of results

• classification and recognition

from paddleocr import PaddleOCR
ocr = PaddleOCR(use_angle_cls=True, lang='en') # need to run only once to load model into memory
img_path = 'PaddleOCR/doc/imgs_words_en/word_10.png'
result = ocr.ocr(img_path, det=False, cls=True)
for idx in range(len(result)):
    res = result[idx]
    for line in res:
        print(line)

Output will be a list, each item contains recognition text and confidence

['PAIN', 0.990372]

• only detection

from paddleocr import PaddleOCR,draw_ocr
ocr = PaddleOCR() # need to run only once to download and load model into memory
img_path = 'PaddleOCR/doc/imgs_en/img_12.jpg'
result = ocr.ocr(img_path,rec=False)
for idx in range(len(result)):
    res = result[idx]
    for line in res:
        print(line)

# draw result
from PIL import Image
result = result[0]
image = Image.open(img_path).convert('RGB')
im_show = draw_ocr(image, result, txts=None, scores=None, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')

Output will be a list, each item only contains bounding box

[[756.0, 812.0], [805.0, 812.0], [805.0, 830.0], [756.0, 830.0]]
[[820.0, 803.0], [1085.0, 801.0], [1085.0, 836.0], [820.0, 838.0]]
[[393.0, 801.0], [715.0, 805.0], [715.0, 839.0], [393.0, 836.0]]
......

Visualization of results

• only recognition

from paddleocr import PaddleOCR
ocr = PaddleOCR(lang='en') # need to run only once to load model into memory
img_path = 'PaddleOCR/doc/imgs_words_en/word_10.png'
result = ocr.ocr(img_path, det=False, cls=False)
for idx in range(len(result)):
    res = result[idx]
    for line in res:
        print(line)

Output will be a list, each item contains recognition text and confidence

['PAIN', 0.990372]

• only classification

from paddleocr import PaddleOCR
ocr = PaddleOCR(use_angle_cls=True) # need to run only once to load model into memory
img_path = 'PaddleOCR/doc/imgs_words_en/word_10.png'
result = ocr.ocr(img_path, det=False, rec=False, cls=True)
for idx in range(len(result)):
    res = result[idx]
    for line in res:
        print(line)

Output will be a list, each item contains classification result and confidence

['0', 0.99999964]

2.2 Use by command line

show help information

paddleocr -h

• detection classification and recognition

paddleocr --image_dir PaddleOCR/doc/imgs_en/img_12.jpg --use_angle_cls true --lang en

Output will be a list, each item contains bounding box, text and recognition confidence

[[[441.0, 174.0], [1166.0, 176.0], [1165.0, 222.0], [441.0, 221.0]], ('ACKNOWLEDGEMENTS', 0.9971134662628174)]
[[[403.0, 346.0], [1204.0, 348.0], [1204.0, 384.0], [402.0, 383.0]], ('We would like to thank all the designers and', 0.9761400818824768)]
[[[403.0, 396.0], [1204.0, 398.0], [1204.0, 434.0], [402.0, 433.0]], ('contributors who have been involved in the', 0.9791957139968872)]
......

pdf file is also supported, you can infer the first few pages by using the page_num parameter, the default is 0, which means infer all pages

paddleocr --image_dir ./xxx.pdf --use_angle_cls true --use_gpu false --page_num 2

• detection and recognition

paddleocr --image_dir PaddleOCR/doc/imgs_en/img_12.jpg --lang en

Output will be a list, each item contains bounding box, text and recognition confidence

[[[441.0, 174.0], [1166.0, 176.0], [1165.0, 222.0], [441.0, 221.0]], ('ACKNOWLEDGEMENTS', 0.9971134662628174)]
[[[403.0, 346.0], [1204.0, 348.0], [1204.0, 384.0], [402.0, 383.0]], ('We would like to thank all the designers and', 0.9761400818824768)]
[[[403.0, 396.0], [1204.0, 398.0], [1204.0, 434.0], [402.0, 433.0]], ('contributors who have been involved in the', 0.9791957139968872)]
......

• classification and recognition

paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --use_angle_cls true --det false --lang en

Output will be a list, each item contains text and recognition confidence

['PAIN', 0.9934559464454651]

• only detection

paddleocr --image_dir PaddleOCR/doc/imgs_en/img_12.jpg --rec false

Output will be a list, each item only contains bounding box

[[397.0, 802.0], [1092.0, 802.0], [1092.0, 841.0], [397.0, 841.0]]
[[397.0, 750.0], [1211.0, 750.0], [1211.0, 789.0], [397.0, 789.0]]
[[397.0, 702.0], [1209.0, 698.0], [1209.0, 734.0], [397.0, 738.0]]
......

• only recognition

paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --det false --lang en

Output will be a list, each item contains text and recognition confidence

['PAIN', 0.9934559464454651]

• only classification

paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --use_angle_cls true --det false --rec false

Output will be a list, each item contains classification result and confidence

['0', 0.99999964]

3 Use custom model

When the built-in model cannot meet the needs, you need to use your own trained model. First, refer to export doc to convert your det and rec model to inference model, and then use it as follows

3.1 Use by code

from paddleocr import PaddleOCR,draw_ocr
# The path of detection and recognition model must contain model and params files
ocr = PaddleOCR(det_model_dir='{your_det_model_dir}', rec_model_dir='{your_rec_model_dir}', rec_char_dict_path='{your_rec_char_dict_path}', cls_model_dir='{your_cls_model_dir}', use_angle_cls=True)
img_path = 'PaddleOCR/doc/imgs_en/img_12.jpg'
result = ocr.ocr(img_path, cls=True)
for idx in range(len(result)):
    res = result[idx]
    for line in res:
        print(line)

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

3.2 Use by command line

paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --det_model_dir {your_det_model_dir} --rec_model_dir {your_rec_model_dir} --rec_char_dict_path {your_rec_char_dict_path} --cls_model_dir {your_cls_model_dir} --use_angle_cls true

4 Use web images or numpy array as input

4.1 Web image

• Use by code

from paddleocr import PaddleOCR, draw_ocr
ocr = PaddleOCR(use_angle_cls=True, lang="ch") # need to run only once to download and load model into memory
img_path = 'http://n.sinaimg.cn/ent/transform/w630h933/20171222/o111-fypvuqf1838418.jpg'
result = ocr.ocr(img_path, cls=True)
for idx in range(len(result)):
    res = result[idx]
    for line in res:
        print(line)

# show result
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='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')

• Use by command line

paddleocr --image_dir http://n.sinaimg.cn/ent/transform/w630h933/20171222/o111-fypvuqf1838418.jpg --use_angle_cls=true

4.2 Numpy array

Support numpy array as input only when used by code

import cv2
from paddleocr import PaddleOCR, draw_ocr, download_with_progressbar
ocr = PaddleOCR(use_angle_cls=True, lang="ch") # need to run only once to download and load model into memory
img_path = 'PaddleOCR/doc/imgs/11.jpg'
img = cv2.imread(img_path)
# img = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY), If your own training model supports grayscale images, you can uncomment this line
result = ocr.ocr(img, cls=True)
for idx in range(len(result)):
    res = result[idx]
    for line in res:
        print(line)

# show result
from PIL import Image
result = result[0]
download_with_progressbar(img_path, 'tmp.jpg')
image = Image.open('tmp.jpg').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/fonts/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')

5 PDF file

• Use by command line

you can infer the first few pages by using the page_num parameter, the default is 0, which means infer all pages

paddleocr --image_dir ./xxx.pdf --use_angle_cls true --use_gpu false --page_num 2

• Use by code

from paddleocr import PaddleOCR, draw_ocr

# Paddleocr supports Chinese, English, French, German, Korean and Japanese.
# You can set the parameter `lang` as `ch`, `en`, `fr`, `german`, `korean`, `japan`
# to switch the language model in order.
ocr = PaddleOCR(use_angle_cls=True, lang="ch"， page_num=2)  # need to run only once to download and load model into memory
img_path = './xxx.pdf'
result = ocr.ocr(img_path, cls=True)
for idx in range(len(result)):
    res = result[idx]
    for line in res:
        print(line)

# draw result
import fitz
from PIL import Image
import cv2
import numpy as np
imgs = []
with fitz.open(img_path) as pdf:
    for pg in range(0, pdf.pageCount):
        page = pdf[pg]
        mat = fitz.Matrix(2, 2)
        pm = page.getPixmap(matrix=mat, alpha=False)
        # if width or height > 2000 pixels, don't enlarge the image
        if pm.width > 2000 or pm.height > 2000:
            pm = page.getPixmap(matrix=fitz.Matrix(1, 1), alpha=False)

        img = Image.frombytes("RGB", [pm.width, pm.height], pm.samples)
        img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
        imgs.append(img)
for idx in range(len(result)):
    res = result[idx]
    image = imgs[idx]
    boxes = [line[0] for line in res]
    txts = [line[1][0] for line in res]
    scores = [line[1][1] for line in res]
    im_show = draw_ocr(image, boxes, txts, scores, font_path='doc/fonts/simfang.ttf')
    im_show = Image.fromarray(im_show)
    im_show.save('result_page_{}.jpg'.format(idx))

6 Parameter Description