Shulou(Shulou.com)05/31 Report--

Today Xiaobian to share with you how to use Python code to achieve character recognition function of the relevant knowledge, detailed content, clear logic, I believe that most people still know too much about this knowledge, so share this article for your reference, I hope you will learn something after reading this article, let's take a look at it.

1. Environment and configuration requirements

As a whole, it is implemented in Python, and the third-party libraries that need to be used include aip, PIL, keyboard and pyinstaller. If it is not installed, you can install it in CMD using the pip install Baidu-AIP/pillow/keyboard/pyinstaller instruction.

Baidu interface

Open the URL, if you are not registered, please register first, then log in to the management console, click on the left product service → artificial intelligence → text recognition, click to create an application, enter an application name such as Baidu_OCR, select a purpose such as study office, and finally carry on a simple application description, you can click to create immediately. A list of applications appears, including AppID, API Key, Secret Key, and so on, which will be used later.

two。 Specific implementation steps

The general idea of the whole program is, after using the screenshot software to get the screenshot, give it to the Baidu interface to identify and return the result, of course, it can also be the local picture recognition. I use the QQ screenshot software, the shortcut key CTRL+ALT+An is used to open the screenshot, after selecting the screenshot area, press the Enter key to save it to the pasteboard, or you can use other screenshot software.

Get screenshot

The keyboard class library is used to listen for keyboard movements, so after a shortcut key is pressed, there will be a corresponding action. And use the ImageGrab in PIL to get the picture in the clipboard and generate the local picture file.

# 1. Screenshot keyboard.wait ('ctrl+alt+a') print (' start screenshot') keyboard.wait ('enter') print (' save screenshot') time.sleep (0.1) # 2. Save picture image = ImageGrab.grabclipboard () image.save ('img.png') call Baidu aip to recognize and print text

First initialize the application with the AppID, API Key and Secret Key generated at the time of registration, then read the saved picture and print the recognized text.

With open ('img.png',' rb') as fp: image = fp.read () text_list = client.basicAccurate (image) ['words_result'] for text in text_list: print (text [' words'])

The running result is shown in the figure:

We can also add an infinite loop to keep taking screenshots.

Call the packaging program to generate exclusive identification text Mini Program

Use pyinstaller library to achieve Mini Program packaging, generate .exe file, so that you can recognize the text at any time. Use pyinstaller xxx.py to package the generated exe file on the command line, and finally you can find the xxx.exe file in the generated dist folder as follows:

Finally, the entire source code is attached:

# introduce screenshot software, get the file to the local end, and identify the picture text, and finally pack import keyboard # control keyboard from PIL import ImageGrab # to save the picture import timefrom aip import AipOcr "" your APPID AK SK "" APP_ID = '17076767'API_KEY =' Af3Rj5HALMz5AN8prSgwTH4m'SECRET_KEY ='* 'client = AipOcr (APP_ID, API_KEY, SECRET_KEY) I = 0while True: # 1. Screenshot keyboard.wait ('ctrl+alt+a') print (' start screenshot') keyboard.wait ('enter') print (' save screenshot') time.sleep (0.1) # 2. Save picture image = ImageGrab.grabclipboard () image.save ('img {} .png' .format (I)) "" invoke universal text recognition (high precision version) "with open ('img {} .png' .format (I)) 'rb') as fp: image = fp.read () text_list = client.basicAccurate (image) [' words_result'] for text in text_list: print (text ['words']) iTunes 1

A case of picture recognition with drawings

These are all the contents of the article "how to use Python code to achieve character recognition". Thank you for reading! I believe you will gain a lot after reading this article. The editor will update different knowledge for you every day. If you want to learn more knowledge, please pay attention to the industry information channel.

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.