Shulou(Shulou.com)06/01 Report--

This article introduces the knowledge of "how to use the PaddleOCR library of python". Many people will encounter such a dilemma in the operation of actual cases, so let the editor lead you to learn how to deal with these situations. I hope you can read it carefully and be able to achieve something!

Description

1. PaddleOCR is an ocr recognition library based on deep learning. The accuracy of Chinese recognition is quite good, and it can meet most of the needs of text extraction.

2. Three dependent libraries need to be installed in turn, and the shapely library may be affected by the system, resulting in installation errors.

Install the command pip install paddlepaddlepip install shapelypip install paddleocr code to implement ocr = PaddleOCR (use_angle_cls=True,) # enter the path of the picture to be identified img_path = r "d:Desktop4A34A16F-6B12-4ffc-88C6-FC86E4DF6912.png" # output result save path result = ocr.ocr (img_path Cls=True for line in result: print (line) from PIL import Imageimage = 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) im_show = Image.fromarray (im_show) im_show.show ()

Content extension:

Brief introduction

PaddleOCR aims to create a rich, leading and practical library of OCR tools to help users train better models and apply them to the ground.

Recent update

2020.8.26 Update 84 frequently asked questions and answers related to OCR, refer to FAQ for more information

2020.8.24 PaddleOCR is supported for installation through whl package. For more information, please see Paddleocr Package usage instructions.

2020.8.21 update bilibili live broadcast lesson playback and PPT on August 18, session 2, easy to learn and use OCR tool gift package, get the address

2020.8.16 Open Source text Detection algorithm SAST and text recognition algorithm SRN

2020.7.23 released bilibili live broadcast lesson playback and PPT on July 21. Lesson 1: comprehensive interpretation of the open source gift package of PaddleOCR to obtain the address.

2020.7.15 add mobile DEMO based on EasyEdge and Paddle-Lite to support iOS and Android systems

Characteristics

Super lightweight Chinese OCR model, the total model is only 8.6m

Single model supports combination recognition of Chinese and English numbers, vertical text recognition and long text recognition.

Detection model DB (4.1m) + recognition model CRNN (4.5m)

Practical and general Chinese OCR model

Multiple predictive reasoning deployment scenarios, including service deployment and end-to-side deployment

Multiple text detection training algorithms, EAST, DB, SAST

Multiple text recognition training algorithms, Rosetta, CRNN, STAR-Net, RARE, SRN

Can run on Linux, Windows, MacOS and other systems

This is the end of the content of "how to use python's PaddleOCR Library". Thank you for reading. If you want to know more about the industry, you can follow the website, the editor will output more high-quality practical articles for you!

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.