5 lines of code identify various verification codes

A group friend shared a new library , Try it and find it very practical , I want to share it with you today .

Github Address ：https://github.com/sml2h3/ddddocr

The library name is also very interesting —— ddddocr（ Homophonic band OCR）

Environmental requirements ：

python >= 3.8
Windows/Linux/Macox..

You can install it with the following command

pip install ddddocr

Parameter description ：

I randomly looked for a verification code picture on the Internet , Use this library to practice .

source ： Baidu search

import ddddocr

ocr = ddddocr.DdddOcr()
with open('1.png', 'rb') as f:
    img_bytes = f.read()
res = ocr.classification(img_bytes)

print(res)

Successfully recognized the verification code text ！

And the advantages are also very obvious ： First of all, the code is very concise , Compare the two methods mentioned above , There is no need to set additional environment variables, etc ,5 One line of code can easily identify the verification code picture . On the other hand , We use magic commands %%time Did you test it , This code recognition speed is very fast .

Let's continue the test with more verification code pictures ：

I looked for it again 6 A verification code picture to test , Observations , It is found that this kind of simple verification code can be recognized quickly . But some of the results are problematic —— Letters are not case sensitive （ For example 6 A picture ）.

To make a long story short , If you need verification code identification , And the accuracy requirement is not too high .

that , Take your brother OCR（ddddocr） This library is a good choice ~