Facial beauty classification method of woman image by adopting computer

Abstract

The invention provides a facial beauty classification method of a woman image by adopting a computer, wherein, a C4.5 decision tree learning method is used for building a classifier, and 17-dimensional characteristic quantity is used as a superficial characteristic quantity of facial beauty degree to classify the facial beauty of the woman image. The method in the invention is simple and effective, proving the practicality of intelligent perception of facial beauty by utilizing the method of machine learning, in particular having higher and exciting classification accuracy degree towards the perception of obvious beauty; the test result simultaneously proves that obvious beauty really has objectively existent and quantitative regulations.

Description

technical field [0001] The invention belongs to the field of human face beauty evaluation by computer image processing, and in particular relates to a human face beauty classification method for female images by using a computer. technical background [0002] Computer and information processing science uses computer image processing, machine learning and other methods to conduct more objective research reports on the evaluation of human face beauty. In recent years, some scholars have begun to pay attention. The existing research results are mainly as follows: [0003] 1. Parham et al established an automatic scoring system for the beauty of faces. The beauty judgment is divided into 3 levels, and the 8 distance ratios on the face are extracted as 8-dimensional feature vectors. A variant of the K-nearest algorithm is used. According to the feature vector and Artificial beauty rating is trained on 40 face images, and the test set is another 40 images, with a classification ac...

AI Technical Summary

Problems solved by technology

[0008] (1) The number of face images used as experimental data is not sufficient;

[0009] (2) The distribution of facial beauty is not wide enough, and these factors have a direct impact on the robustness and reliability of the classifier;

[0010] (3) The validity of the adopted proportional features such as the golden ratio is not ideal;

[0011] (4) The above studies are all aimed at the beauty evaluation of Western faces. Whether these methods are effective for the beauty evaluation of Orientals, especially Chinese women, is worthy of verification

[0012] So far, no relevant research reports have been found on the automatic classification of Chinese facial beauty using machine learning methods

Images