A Bimodal Biometric Verification System Based on Deep Learning
Pages 89 - 93
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.
References
[1]
Zhang H, Patel V M, Chellappa R, "Low-Rank and Joint Sparse Representations for Multi-Modal Recognition," IEEE Transactions on Image Processing, vol. 26, no. 10, 2017, pp. 4741--4752.
[2]
Rath S K, Rautaray S S, "A Survey on Face Detection and Recognition Techniques in Different Application Domain," International Journal of Modern Education and Computer Science, vol. 6, no. 8, 2014, pp. 34.
[3]
D M. Vatsa, R. Singh, and A. Noore, "Context switching algorithm for selective multibiometric fusion," Pattern Recognition and Machine in Intelligence. Springer, 2009, pp. 452--457.
[4]
Peralta D, Triguero I, García S, "Distributed incremental fingerprint identification with reduced database penetration rate using a hierarchical classification based on feature fusion and selection," Knowledge-Based Systems, vol.126, 2017, pp. 91--103.
[5]
Liao S, Jain A K, Li S Z, "A fast and accurate unconstrained face detector," IEEE transactions on pattern analysis and machine intelligence, vol.38, no. 2, 2016, pp. 211--223.
[6]
R AbdAlmageed W, Wu Y, Rawls S, "Face recognition using deep multi-pose representations," Applications of Computer Vision (WACV), 2016 IEEE Winter Conference on. IEEE, 2016, pp. 1--9.
[7]
Cumani S, Vair C, Colibro D E, "Fast speaker recognition scoring using I-vector posteriors and probabilistic linear discriminant analysis," June 2016, U.S. Patent 9,373,330.
[8]
Chengwei Huang, Baolin Song, and Li Zhao, "Emotional speech feature normalization and recognition based on speaker-sensitive feature clustering," International Journal of Speech Technology, vol.19, no. 4, 2016, pp. 805--816.
[9]
Stolcke A, Ryant N, Mitra V, "Highly accurateacoustic segmentation using boundary correction models and system fusion," Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on. IEEE, 2014, pp. 5552--5556.
[10]
Hasebe Y, "Design and Implementation of an Online Corpus of Presentation Transcripts of TED Talks," Procedia-Social and Behavioral Sciences, vol.198, 2015, pp. 174--182.
[11]
Ritter M, Mueller M, Stueker S, "Training Deep Neural Networks for Reverberation Robust Speech Recognition," Speech Communication; 12. ITG Symposium; Proceedings of. VDE, 2016, pp. 1--5.
[12]
Schroff F, Kalenichenko D, Philbin J, "Facenet: A unified embedding for face recognition and clustering," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, pp. 815--823.
Index Terms
- A Bimodal Biometric Verification System Based on Deep Learning
Recommendations
Combining sclera and periocular features for multi-modal identity verification
In this paper, we propose to combine sclera and periocular features for identity verification. The proposal is particularly useful in applications related to face recognition when the face is partially occluded with only periocular region revealed. Due ...
Hand-based multimodal biometric fusion: A review
AbstractOver the past few decades, hand-based multimodal biometrics systems have achieved significant attention because of their high security, accuracy, and anti-counterfeiting. Various hand physiological biometric modalities have been explored for ...
Graphical abstractDisplay Omitted
Highlights- Presented a comprehensive overview of hand-based multimodal biometric fusion.
- Introduced the characteristics of four levels of hand-based biometrics.
- Summarized the recent hand-based multimodal biometrics methods based on six ...
A method towards biometric feature fusion
For multimodal biometric person recognition, information fusion can be classified into several levels: rank, decision, sensor, feature and match-score levels. In this paper, a novel method is proposed to fuse information from two or more biometric ...
Comments
Information & Contributors
Information
Published In
December 2017
272 pages
ISBN:9781450353830
DOI:10.1145/3177404
Copyright © 2017 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
In-Cooperation
- Nanyang Technological University
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 27 December 2017
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICVIP 2017
ICVIP 2017: International Conference on Video and Image Processing
December 27 - 29, 2017
Singapore, Singapore
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 80Total Downloads
- Downloads (Last 12 months)3
- Downloads (Last 6 weeks)1
Reflects downloads up to 10 Aug 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in