I tried scoring a transvestite contest using Face ++'s Detect API

This article is the 20th day article of Hands Lab Advent Calendar 2019

Self-introduction

My name is @jxxpsame and I joined the company in October of this year. I touch Unicage mystery technology every day.

I haven't output anything in a blog-like format like this since yahoo! Blog when I was in junior high school, so I'm nervous.

Overview

I used Face ++'s Detect API to score a crossdressing contest for a certain team.

Motivation

――Because there was a tendency to learn python with the team I belong to, I was studying ――Because you are a fan of a certain team --I wanted to try something using the API ―― ~~ I wish I could be happy because I only need my relatives ~~

environment

• OS
• MacOS Catalina --Language
• Python 3.8 --API used -Detect API of Face ++

What is Face ++

The name of the face recognition platform developed by Megvii in Beijing. Face ++'s Detect API can authenticate faces and get various attributes. This time, we will score using the attribute called Beauty Score from among those attributes.

In addition, I referred to the following article for how to use Face ++. I analyzed Pairs with python ~ Face photo ~ Introduction of Face ++ API that detects the face when you send a photo and tells you the facial deviation value

Target of scoring

7 participants in a crossdressing contest of a certain team (Imamura Ishikawa Takahashi Yamashita Togoh Naoe Yokogawa) I used the image uploaded below. Instagram

Source

import requests
import json
import pprint

# API
# key:Person name value:Declare the URL of the image as a dictionary
url_dict = {'Person name:Image URL'}

#Number loop of target people
for img_data in url_dict.items():
    response = requests.post(
        'https://api-us.faceplusplus.com/facepp/v3/detect',
        {
            'api_key': "[Face++API Key obtained from]",
            'api_secret': "[Face++API Seacret obtained from]",
            'image_url': img_data[1], #Image URL
            'return_attributes': 'beauty' #Attributes you want to get
        }
    )

    #json plastic surgery
    json_dict = json.loads(response.text)
    print(img_data[0]) #Person name output
    pprint.pprint(json_dict['faces'][0]['attributes']['beauty'])

result

Please refer to the link of the Instagram post page for each player's name. Imamura {'female_score': 77.524, 'male_score': 78.338} Ishikawa {'female_score': 88.169, 'male_score': 84.546} Takahashi {'female_score': 79.26, 'male_score': 76.487} Yamashita {'female_score': 76.926, 'male_score': 78.077} Togoh {'female_score': 82.532, 'male_score': 81.738} Naoe {'female_score': 78.401, 'male_score': 79.444} Yokogawa {'female_score': 71.818, 'male_score': 69.508}

This time, we will hire the femele_score because it is a transvestite contest. ** The winner was Ishikawa! ** **

By the way

Compared with the actual ranking, it is as follows.

reference 7 giants dressed as beautiful women! 1st place Shingo Ishikawa and others makeover

Except for Togoh and Imamura, the results were almost the same as the actual ranking. Face ++ Scary.

bonus

I was reluctant to use only the face of another person for sample data, so I measured the beauty score of my own face (25 years old, male).

'beauty': {'female_score': 67.239, 'male_score': 62.417},

Cusso is low ... Since femele_score was higher, I added gender (gender) and age (age) to the attributes to be acquired, and measured again. {'age': {'value': 34}, 'beauty': {'female_score': 67.253, 'male_score': 62.442}, 'gender': {'value': 'Female'}}

Everyone at Hands Lab. I look forward to working with you as a 34-year-old woman.

Hands Lab Advent Calendar 2019 Day 21 is @jnuank: clap :: clap: