Abstract
Multimodal biometrics combine a variety of biological features to have a significant impact on identification performance, which is a newly developed trend in biometrics identification technology. This study proposes a novel multimodal biometrics recognition model based on the stacked extreme learning machines (ELMs) and canonical correlation analysis (CCA) methods. The model, which has a symmetric structure, is found to have high potential for multimodal biometrics. The model works as follows. First, it learns the hidden-layer representation of biological images using extreme learning machines layer by layer. Second, the canonical correlation analysis method is applied to map the representation to a feature space, which is used to reconstruct the multimodal image feature representation. Third, the reconstructed features are used as the input of a classifier for supervised training and output. To verify the validity and efficiency of the method, we adopt it for new hybrid datasets obtained from typical face image datasets and finger-vein image datasets. Our experimental results demonstrate that our model performs better than traditional methods.
Highlights
The field of biometrics has gained attention globally because of its broad application prospects, and huge social and economic benefits
We compare the proposed method with other deep-learning methods mentioned in the literature, such as Stacked Auto-Encoder (SAE) [3] and Deep Belief Nets (DBN) [5]
This paper presents a new kind of multimodal biometrics recognition network model named the S-E-C model, based on stacked extreme learning machines (ELMs) and canonical correlation analysis (CCA) methods
Summary
The field of biometrics has gained attention globally because of its broad application prospects, and huge social and economic benefits. It could affect the performance of a single-mode biometric identification system that has biometrically detected “noise” (such as a fingerprint with a scar or a changed voice due to a cold). Deep learning is a promising study of machine learning, and it has recently gained more attention. Many studies show that a deep network with a multiple hidden-layer neural network architecture has the advantage of mining effective information fully for data, and it can successfully achieve unsupervised learning of single-mode data (text, images, voice, etc.) [2], which inspires the multimodal deep learning.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
