Gender identification method and system based on multispectral fusion, storage medium and terminal

Abstract

The invention belongs to the technical field of digital image processing and pattern recognition, and discloses a gender recognition method and system based on multispectral fusion, a storage medium and a terminal. A camera with multiple wavebands is utilized for acquiring a face image and performing image preprocessing. A convolutional neural network module is used for subsequent face image feature learning; respectively pre-training the visible light and the infrared rays of each sub-band to obtain respective pre-training model parameters; connecting the network modules corresponding to thevisible light and the sub-band infrared rays in parallel, and adding a multispectral feature fusion layer at the tail end of the network; and adding a full connection layer behind the parallel fusiontype neural network for identification and classification, and performing retraining by using multispectral data to obtain a final gender identification result. When the method is implemented, specific fusion sub-bands can be selected and combined from five sub-bands of visible light, near infrared, short-wave infrared, medium-wave infrared and long-wave infrared; and the method has the characteristics of high precision and relatively high robustness.

Description

technical field [0001] The invention belongs to the technical field of digital image processing and pattern recognition, and in particular relates to a gender recognition method, system, storage medium and terminal based on multispectral fusion. Background technique [0002] At present, the world has entered the information age in an all-round way, and gender information in modern society is an important demographic attribute that cannot be ignored. In recent years, since the gender information of population attributes has been widely used in personnel monitoring, population research, content indexing, targeted advertising and other fields, research on using computer vision technology to identify gender attributes has gained great attention. [0003] Traditional gender recognition methods are mostly based on various manually designed feature extraction operators and classifiers. This type of method is complex in design, low in precision, and poor in robustness. It is difficu...

AI Technical Summary

Problems solved by technology

[0005] (1) Traditional gender recognition methods are mostly based on various manually designed feature extraction operators and classifiers. This type of method is complex in design, low in accuracy, and poor in robustness. It is difficult to accurately identify gender in complex environments. It is increasingly difficult to meet the current gender identification needs

[0006] (2) At present, most gender recognition technologies use visible light imaging methods. This type of technology is limited to good conditions with sufficient light during the day, and usually performs poorly in environments such as insufficient light and harsh weather, and it is difficult to meet various complex environments in the real world.

How to design a convolutional neural network structure that includes a feature fusion layer to achieve multispectral feature fusion is a very challenging task. At present, there are few researches on this problem in the industry.

Images