Class Representative Autoencoder for Low Resolution Multi-Spectral Gender Classification
This addresses gender classification in unconstrained scenarios for applications like security and marketing, but it is incremental as it builds on existing autoencoder methods.
The paper tackles gender classification in low-resolution multi-spectral face images by proposing a Class Representative Autoencoder (AutoGen) that minimizes intra-class and maximizes inter-class variations in features, achieving results that outperform existing approaches and commercial systems.
Gender is one of the most common attributes used to describe an individual. It is used in multiple domains such as human computer interaction, marketing, security, and demographic reports. Research has been performed to automate the task of gender recognition in constrained environment using face images, however, limited attention has been given to gender classification in unconstrained scenarios. This work attempts to address the challenging problem of gender classification in multi-spectral low resolution face images. We propose a robust Class Representative Autoencoder model, termed as AutoGen for the same. The proposed model aims to minimize the intra-class variations while maximizing the inter-class variations for the learned feature representations. Results on visible as well as near infrared spectrum data for different resolutions and multiple databases depict the efficacy of the proposed model. Comparative results with existing approaches and two commercial off-the-shelf systems further motivate the use of class representative features for classification.