Human face aesthetic prediction method based on combination of biologically inspired computation and deep attribute learning

Abstract

The invention provides a human face aesthetic prediction method based on the combination of the biologically inspired computation and the deep attribute learning, and relates to a human face aestheticprediction method. According to the method, firstly, the eye movement information of a user is acquired when the user observes a human face image through an eye view monitoring system. After that, the aesthetic space area when the user looks at a human face is further extracted. The aesthetic space area is divided into a plurality of characteristic spaces through clustering. After that, a human face aesthetic detector is trained through the supervised learning method of the convolution neural network, wherein the obtained human face aesthetic detector can be used for preprocessing a frontal face image and then obtaining the aesthetic level of the face image. The aesthetic space area when the user observes the image is extracted by collecting the middle-layer attribute characteristic information of the image. The aesthetic characteristic area for determining the face aesthetic level is fully verified through an obtained human face aesthetic model. Meanwhile, compared with other human face aesthetic evaluation methods, the accuracy of the method is greatly improved.

Description

technical field [0001] The invention relates to a method for predicting human face beauty, in particular to a method for predicting human face beauty based on the combination of biological inspiration and deep attribute learning. Background technique [0002] In the current face-related applications, face aesthetic prediction has attracted more and more people's attention, and related applications have also been obtained on the client and mobile terminals. For example, when the user takes a face photo, a current face is returned in real time. The beauty score of , helping people find the ideal angle for taking pictures. However, the most critical challenge in the current face aesthetic technology is to extract features with discriminative and perceptual capabilities to distinguish the beauty of human faces. So far, the existing methods to describe the beauty of human faces mainly rely on the manually extracted underlying features of the image, such as the calculation of the...

AI Technical Summary

Problems solved by technology

[0004] The above two methods cannot reveal the effective expression of image semantic information. Although the method based on geometric features is also relevant to the analysis of facial beauty, it still cannot clearly explain how the human brain uses these geometric features to analyze and distinguish facial features. The beauty of the human face does not use scientific methods to count and verify its rationality

For the aesthetic analysis method based on global features, there are many regions and noises that the human brain does not pay attention to, and there may be irreversible effects on the discrimination of facial aesthetics.

Images