Gender and Ethnicity Classification of Iris Images using Deep Class-Encoder

TL;DR

This paper introduces a novel supervised autoencoder called Deep Class-Encoder for classifying ethnicity and gender from iris images, demonstrating improved accuracy over existing methods.

Contribution

The paper proposes a new deep autoencoder model that leverages class labels to learn discriminative features for ethnicity and gender classification from iris images.

Findings

Effective in improving classification accuracy

Outperforms existing approaches and state-of-the-art methods

Validated on two datasets for each classification task

Abstract

Soft biometric modalities have shown their utility in different applications including reducing the search space significantly. This leads to improved recognition performance, reduced computation time, and faster processing of test samples. Some common soft biometric modalities are ethnicity, gender, age, hair color, iris color, presence of facial hair or moles, and markers. This research focuses on performing ethnicity and gender classification on iris images. We present a novel supervised autoencoder based approach, Deep Class-Encoder, which uses class labels to learn discriminative representation for the given sample by mapping the learned feature vector to its label. The proposed model is evaluated on two datasets each for ethnicity and gender classification. The results obtained using the proposed Deep Class-Encoder demonstrate its effectiveness in comparison to existing approaches and state-of-the-art methods.