Are you eligible? Predicting adulthood from face images via class specific mean autoencoder

TL;DR

This paper introduces a novel deep learning autoencoder that learns class-specific features to accurately classify whether face images belong to adults or minors, addressing a complex age-related recognition challenge.

Contribution

The paper proposes a class specific mean autoencoder that enhances intra-class feature similarity for improved adulthood classification from face images.

Findings

Higher classification accuracy than existing algorithms

Effective in distinguishing adults from minors

Outperforms commercial off-the-shelf systems

Abstract

Predicting if a person is an adult or a minor has several applications such as inspecting underage driving, preventing purchase of alcohol and tobacco by minors, and granting restricted access. The challenging nature of this problem arises due to the complex and unique physiological changes that are observed with age progression. This paper presents a novel deep learning based formulation, termed as Class Specific Mean Autoencoder, to learn the intra-class similarity and extract class-specific features. We propose that the feature of a particular class if brought similar/closer to the mean feature of that class can help in learning class-specific representations. The proposed formulation is applied for the task of adulthood classification which predicts whether the given face image is of an adult or not. Experiments are performed on two large databases and the results show that the proposed algorithm yields higher classification accuracy compared to existing algorithms and a Commercial-Off-The-Shelf system.