Multi-Level Feature Abstraction from Convolutional Neural Networks for Multimodal Biometric Identification

TL;DR

This paper introduces a deep multimodal fusion network that combines features from multiple CNN layers across face, iris, and fingerprint modalities, significantly improving person identification accuracy over unimodal methods.

Contribution

The paper presents a novel multi-level feature fusion approach in deep CNNs for multimodal biometric identification, optimizing multiple abstraction levels jointly for enhanced performance.

Findings

Multi-level feature fusion outperforms single-layer fusion.

Joint optimization improves identification accuracy.

Significant parameter reduction with multi-level features.

Abstract

In this paper, we propose a deep multimodal fusion network to fuse multiple modalities (face, iris, and fingerprint) for person identification. The proposed deep multimodal fusion algorithm consists of multiple streams of modality-specific Convolutional Neural Networks (CNNs), which are jointly optimized at multiple feature abstraction levels. Multiple features are extracted at several different convolutional layers from each modality-specific CNN for joint feature fusion, optimization, and classification. Features extracted at different convolutional layers of a modality-specific CNN represent the input at several different levels of abstract representations. We demonstrate that an efficient multimodal classification can be accomplished with a significant reduction in the number of network parameters by exploiting these multi-level abstract representations extracted from all the modality-specific CNNs. We demonstrate an increase in multimodal person identification performance by utilizing the proposed multi-level feature abstract representations in our multimodal fusion, rather than using only the features from the last layer of each modality-specific CNNs. We show that our deep multi-modal CNNs with multimodal fusion at several different feature level abstraction can significantly outperform the unimodal representation accuracy. We also demonstrate that the joint optimization of all the modality-specific CNNs excels the score and decision level fusions of independently optimized CNNs.