Face attribute recognition method and system based on deep learning

Abstract

The invention discloses a face attribute recognition method and system based on deep learning, belongs to the field of human face recognition, and aims to process attributes such as genders, expressions and whether glasses are worn or not with high recognition degree according to a general classification mode. According to the invention, a probability distribution mode is adopted to optimize the attribute with the property of continuous change according to the sequence, and the standard deviation information of each age is fused into the neural network for adaptive learning, so that the precision and stability of face attribute, especially age recognition, are improved, and meanwhile, the running time of the whole system is shortened.

Description

Technical field[0001]The invention belongs to the field of face recognition, and in particular relates to a face attribute recognition method and system based on deep learning.Background technique[0002]With the development of biometric technology, face recognition-related technologies are applied to more and more scenarios. Face attribute recognition is to obtain the age, gender, race and other attribute information of the face image by detecting the face image. It has great application prospects in the fields of human-computer interaction, social networking, and advertising push. In the past ten years, face attribute recognition technology has attracted more and more researchers' attention.[0003]Face attribute recognition is the same as other biometric recognition technologies, and it is mainly divided into two steps: 1. feature extraction; 2. feature recognition. Early researchers mainly used machine learning related algorithms to obtain face attribute information. For feature ext...

AI Technical Summary

Problems solved by technology

[0014] The invention in the patent [CN 107247947 A] has three obvious deficiencies: 1. age standard deviation σ age The setting needs to be based on experience or statistical rules. Let’s not talk about whether the setting method based on experience is reasonable. Even if it is set according to the statistical method, there are not enough statistical samples; probability distribution, and almost all labeled data are single-label, which requires secondary processing; 3. In the age recognition stage, N images should be selected from each age image set and the standard age base should be calculated as prior information. A large number of calculations are required in the process of calculating the final predicted age, which will inevitably lead to a significant increase in the time consumption of the entire recognition system

Images