Cascaded depth neural network-based face attribute recognition method

Abstract

The invention relates to a cascaded depth neural network-based face attribute recognition method. The method includes the following steps that: 1) a cascaded depth neural network composed of a plurality of independent convolution depth neural networks is constructed; 2) a large number of face image data are adopted to train networks at all levels in the cascaded depth neural network level by level, and the output of networks of previous levels is adopted as the input of networks of posterior levels, such that a coarse-to-fine neural network structure can be obtained; and 3) the coarse-to-fine neural network structure is adopted to recognize the attributes of an inputted face image, and final recognition results can be outputted. According to the cascaded depth neural network-based face attribute recognition method of the invention, a cascade algorithm system is adopted based on depth learning, and therefore, training time can be accelerated; and a cascaded coarse-to-fine processing process is realized, and the performance of a final network can be improved by networks of each level through utilizing information of networks of upper levels, and therefore, the speed and the accuracy of face attribute recognition can be effectively improved.

Description

technical field [0001] The invention belongs to the technical field of image processing and face recognition, and in particular relates to a face attribute recognition method based on a cascaded deep neural network. Background technique [0002] The face attribute refers to the attributes such as gender, age, and race of the person that can be obtained from the facial features of the person. The recognition of face attributes can help face recognition be more accurate, and individual face attribute recognition also has many application scenarios. The traditional face attribute recognition method uses artificially designed texture operators plus the shallow structure of traditional classifiers such as SVM, which often cannot obtain more accurate prediction results. [0003] Deep neural network is a relatively hot research direction in recent years. It simulates the multi-layer computing architecture of the human brain from the perspective of bionics. It is the closest to art...

AI Technical Summary

Problems solved by technology

However, deep learning has shortcomings such as training difficulties and long training cycles. Although it has been applied in face attribute recognition and classification, the accuracy and processing speed of face attribute recognition cannot well meet actual needs.

Images