Design of A Beauty Matching App Based on Support Vector Machine

In order to meet consumer's huge demands for cosmetic match, this project plans to develop a cosmetic match application --- Beauty, based on support vector machine. Beauty, according to pictures including different shapes of face, can adopt Principle Component Analysis (PCA) to optimize image p...

Full description

Saved in:
Bibliographic Details
Published in2021 China Automation Congress (CAC) pp. 2116 - 2121
Main Authors Cheng, Xinyue, Yan, Baokang, Peng, Yahui, Wei, Jing, Cao, Yujing, Yu, Zehao
Format Conference Proceeding
LanguageEnglish
Published IEEE 22.10.2021
Subjects
Analytical models
Automation
beauty matching
face classification
Faces
image processing
Kernel
model training
Principal component analysis
Shape
support vector machine
Support vector machine classification
Online AccessGet full text

Cover

More Information
Summary:In order to meet consumer's huge demands for cosmetic match, this project plans to develop a cosmetic match application --- Beauty, based on support vector machine. Beauty, according to pictures including different shapes of face, can adopt Principle Component Analysis (PCA) to optimize image pixel, get the lower dimension feature vector to support vector machine's input, and then adopt cross-validation and grid-search to select penalty parameter c and kernel parameter g to train the model. Finally, different facial pictures are tested respectively by making use of these models. And then consumers can get the most suitable recommendation in accordance with classification results.
ISSN:2688-0938
DOI:10.1109/CAC53003.2021.9727296