Face attribute classification system based on bidirectional ladder structure

Abstract

The present invention relates to the field of computer vision technology, in particular to a face attribute classification system based on a two-way ladder structure, aiming to solve how to make full use of the features of different levels in the deep network, and the correspondence between features of different levels and different face attributes relationship to improve the accuracy of face attribute classification. For this purpose, the face attribute classification system based on the two-way Ladder structure provided by the present invention includes a two-way Ladder self-encoder module, an adaptive attention module and an adaptive scoring fusion module; the two-way Ladder self-encoder module includes an encoder module and a decoder The adaptive attention module includes a plurality of attention submodules; the adaptive score fusion module is configured to obtain the face attribute classification result of the face image to be tested according to the output result of the encoder module and the output result of the attention submodule . Based on the above structure, different levels of encoding features and decoding features can be fully utilized to improve the accuracy of face attribute classification.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a human face attribute classification system based on a bidirectional Ladder structure. Background technique [0002] The face attribute classification method is a method for judging whether a given face image contains a certain face attribute, which is widely used in face recognition, face retrieval, face verification and other fields. At present, the use of deep network for face attribute classification can greatly improve the classification performance, but the deep network mainly focuses on the role of deep features on attribute classification, and shallow features have not been fully exploited and utilized. In addition, the corresponding relationship between the features of different layers of the deep network and different face attributes is not fully utilized, which greatly limits the accuracy of face attribute classification. [0003] Correspondingly, a new face ...

AI Technical Summary

Problems solved by technology

At present, the use of deep network for face attribute classification can greatly improve the classification performance, but the deep network mainly focuses on the role of deep features on attribute classification, and shallow features have not been fully exploited and utilized.

In addition, the corresponding relationship between the features of different layers of the deep network and different face attributes has not been fully utilized, which greatly limits the accuracy of face attribute classification.

Images