51. Build a Small Python project with Baidu API interface

@ the Author: Runsen

This project focuses on image recognition. By invoking Baidu API interface, many humanized functions can be realized, such as gesture recognition, portrait segmentation and appearance level scoring.

This time Gitchat paid for articles, but the subscription was too low. So can only regard as the public number article hair.

This project combines artificial intelligence and GUI graphic interface development to meet users’ needs for image recognition.

Main technical points used in this project:

• Baidu API interface call
• Tkinker
• Opencv calls USB camera

The functional requirements

The main functions of this Python project are to call the computer camera to take photos, and use Baidu API interface to achieve appearance level scoring, gesture recognition and matting.

API documentation for functional requirements:

Appearance rating: https://ai.baidu.com/ai-doc/FACE/yk37c1u4t

Gesture recognition: https://ai.baidu.com/ai-doc/BODY/4k3cpywrv

Portrait segmentation: https://ai.baidu.com/ai-doc/BODY/Fk3cpyxua

Obtain the Access token value

This project adopts the method of encapsulating classes to write the code, and it is necessary to encapsulate the Baidu_API into classes.

The appearance level was rated

Identification results include age, sex, race, appearance level score (0-100)

The result of the above image is 47.34 22 male yellow

Gesture recognition

The recognition results include the Chinese and English meanings of the gestures

The result of the image above: Five, Five

Portrait segmentation matting

The result is a matting of the person

The complete code

"' @ Author: Runsen @ WeChat: RunsenLiu @ WeChat public number: the king of the Python @ CSDN: https://blog.csdn.net/weixin_44510615 @ making: https://github.com/MaoliRUNsen @ Date: 2020/11/29 "'

import requests
import base64

class Baidu_API() :
    def __init__(self) :
        self.headers={'Content-Type': 'application/json; charset=UTF-8'}
        self.AppID = '23061934'  # Baidu application account ID
        self.APIKey = '0EGiM1wDAH5kmFAvhYVLYCbs'  # Authorization for interface access
        self.SecretKey = 'KVugHxxu4uq203b111SwVY2w98Cd9D70'  # key

    Get the access token value
    def get_access_token(self) :
        host = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id= & client_secret = {} {}'.format(self.APIKey,self.SecretKey)
        response = requests.get(host,self.headers)
        if response:
            access_token=response.json()['access_token']
            return access_token
        else:
            print("Failed to obtain access_token")

    Get base64 image data
    def get_img_base64(self,img_path) :
        Read the image in binary format and convert it to base64 format (use the binary to base64 function)
        with open(img_path,'rb')as f:
            # base64 encoding
            img_data = base64.b64encode(f.read())
        return img_data

    # Function 1. Score your appearance level
    def face_detect(self,img_path) :
        try:
            # Access the face detection API
            base_url = "https://aip.baidubce.com/rest/2.0/face/v3/detect"
            # Basic parameters
            request_url = base_url + "? access_token=" + self.get_access_token()

            params = {"image": self.get_img_base64(img_path),
                      "image_type": "BASE64"."face_field": "faceshape,facetype,beauty,age,beauty,glasses,gender,race"}
            # start access
            response = requests.post(url=request_url,
                                      data=params,
                                      headers=self.headers)
            re = response.json()
            score = re["result"] ["face_list"] [0] ['beauty']
            age = re["result"] ["face_list"] [0] ['age']
            gender = re["result"] ["face_list"] [0] ['gender'] ['type']
            race = re["result"] ["face_list"] [0] ['race'] ['type']
            # return data
            print(score,age,gender,race)
            return score,age,gender,race
        except:
            return 'Not correctly recognized, please try again'

    # Feature 2. Gesture recognition
    def gesture(self,img_path) :
        try:
            base_url = 'https://aip.baidubce.com/rest/2.0/image-classify/v1/gesture'
            # Basic parameters
            request_url = base_url + "? access_token=" + self.get_access_token()
            params = {"image": self.get_img_base64(img_path),
                      "image_type": "BASE64"}
            # start access
            response = requests.post(url=request_url,
                                     data=params,
                                     headers=self.headers)  # <class 'requests.models.Response'>

            re = response.json()  # <class 'dict'>
            classname_en = re["result"] [0] ['classname']
            classname_zh = self.translate(classname_en)
            print(classname_en,classname_zh)
            return classname_en,classname_zh
        except:
            return 'Not correctly identified, please try again'


    # Function 3. Portrait segmentation matting
    def body_seg(self,img_path, out_path) :
        try:
            base_url = "https://aip.baidubce.com/rest/2.0/image-classify/v1/body_seg"
            request_url = base_url + "? access_token=" + self.get_access_token()
            params = {"image": self.get_img_base64(img_path)}
            headers = {'content-type': 'application/x-www-form-urlencoded'}
            response = requests.post(request_url, data=params, headers=headers)
            labelmap = base64.b64decode(response.json()['foreground'])
            with open(out_path, 'wb') as fp:
                fp.write(labelmap)
        except:
            return 'Not correctly recognized, please try again'

    # Translation APi interface
    def translate(self, query) :
        url = 'http://fanyi.youdao.com/translate?&doctype=json&type=AUTO&i={}'.format(query)
        r = requests.post(url=url)
        return r.json()['translateResult'] [0] [0] ['tgt'].strip('the')


if __name__ == '__main__':
    Api = Baidu_API()
    Api.face_detect('me.jpg')
    Api.gesture('gesture.jpg')
    Api.body_seg('me.jpg'.'me.png')
Copy the code

GitHub, portal ~, GitHub, portal ~, GitHub, Portal ~