Visible to the public A Bimodal Biometric Verification System Based on Deep Learning

TitleA Bimodal Biometric Verification System Based on Deep Learning
Publication TypeConference Paper
Year of Publication2017
AuthorsSong, Baolin, Jiang, Hao, Zhao, Li, Huang, Chengwei
Conference NameProceedings of the International Conference on Video and Image Processing
PublisherACM
Conference LocationNew York, NY, USA
ISBN Number978-1-4503-5383-0
Keywordsconvolutional neural networks, Deep Learning, deep video, Feature fusion, identity authentication, Metrics, multi-modal biometrics, pubcrawl, resilience, Resiliency, Scalability
Abstract

In order to improve the limitation of single-mode biometric identification technology, a bimodal biometric verification system based on deep learning is proposed in this paper. A modified CNN architecture is used to generate better facial feature for bimodal fusion. The obtained facial feature and acoustic feature extracted by the acoustic feature extraction model are fused together to form the fusion feature on feature layer level. The fusion feature obtained by this method are used to train a neural network of identifying the target person who have these corresponding features. Experimental results demonstrate the superiority and high performance of our bimodal biometric in comparison with single-mode biometrics for identity authentication, which are tested on a bimodal database consists of data coherent from TED-LIUM and CASIA-WebFace. Compared with using facial feature or acoustic feature alone, the classification accuracy of fusion feature obtained by our method is increased obviously.

URLhttps://dl.acm.org/doi/10.1145/3177404.3177410
DOI10.1145/3177404.3177410
Citation Keysong_bimodal_2017