Face beauty evaluation method based on deep learning

Abstract

The invention provides a face beauty evaluation method based on deep learning. The method comprises the following steps: (1), acquiring a trainer face image set and a tester face image set; (2) learning face beauty characteristics of the trainer face image set by virtue of characteristic learning, and convoluting original images by use of a convolution template so as to form multiple characteristic images; (3) by taking the obtained characteristic images as input, learning a second-layer convolution template by use of a same characteristic learning method, and convoluting the characteristic images obtained in the step (2) by use of the convolution template so as to form multiple characteristic images; (4) performing binarization encoding on the obtained characteristic images, calculating and counting histograms in a local region, and then splicing all the counted histograms of the local region into a face image characteristic.; and (5), quantifying face beauty evaluation into multiple equivalence forms, and classifying by use of an SVM (Support Vector Machine) classifier so as to obtain an evaluation result. According to the method, the face beauty characteristics are automatically learned from a sample by virtue of a deep learning algorithm, so that a computer can intelligently evaluate the face beauty.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition and artificial intelligence, in particular to a method for objectively evaluating the beauty degree of a human face by a computer. Background technique [0002] The evaluation of the beauty of a human face is likely to be affected by subjective factors. Different people and different races have different average standards. Even the same nation may have completely different aesthetic standards in different periods. But at the same time, people in the same region still had a common understanding of beauty. Some scholars have begun to use computers to evaluate the beauty of human faces more objectively. Face beauty evaluation can be widely used in daily life, such as allowing computers to evaluate and share beauty for friends in social networks. [0003] The face beauty prediction method based on geometric features is a hot spot in the research of face beauty. Researchers extract many ...

AI Technical Summary

Problems solved by technology

For example, Chinese Invention Patent No. 200810029422.6 "A Video-Based Appraisal Method for Facial Beauty" and No. 200910041044.8 "A Method for Classifying Facial Beauty Using Computers for Female Images". However, face plane images are simply described by geometric features. The feature information that characterizes the beauty of the face, such as the ups and downs of the muscles, the structural turning of the facial features, etc., will be lost, and the detection of face feature points needs to be manually labeled in the training stage, but the intervention of too many subjective factors will easily lead to inaccurate results. Universality, even when the number of images to be labeled is huge, it makes manual intervention very cumbersome

Images