Abstract
Feature-level fusion approaches for multispectral biometrics are mainly grouped into two categories: 1) concatenation and 2) elementwise multiplication. While concatenation of feature vectors has benefits in allowing all elements to interact, it is difficult to learn output classification. Differently, elementwise multiplication has the benefits in enabling multiplicative interaction, but it is difficult to learn input embedding. In this paper, we propose a novel approach to combine the benefits of both categories based on a compact representation of two feature vectors’ outer product, which is called the multimodal compact multi-linear pooling technique. We first propose to expand the bilinear pooling technique for two inputs to a multi-linear technique to accommodate for multiple inputs (multiple inputs from multiple spectra are frequent in the multispectral biometric context). This fusion approach not only allows all elements to interact and enables multiplicative interaction, but also uses a small number of parameters and low computation complexity. Based on this fusion proposal, we subsequently propose a complete multispectral periocular recognition system. Employing higher order spectra features with an elliptical sampling approach proposed by Algashaam et al. , our proposed system achieves the state-of-the-art performance in both our own and the IIIT multispectral periocular data sets. The proposed approach can also be extended to other biometric modalities.
Highlights
Biometrics have been shown to be critical to deal with the increasing incidents of fraud challenges in highly secure identity authentication systems
Multispectral biometric technologies are emerging to address this challenge owing to two major advantages: (1) they offer richer information details for extracting features and (2) they are more robust to spoof attacks since they are more difficult to be duplicated or counterfeited [4]
There are a number of other approaches such as Wild et al [35] who proposed to select and keep the most common bit values for each location in the iris feature vectors. It has not been used for multispectral fusion yet, it is worth noting a body of work in multimodal biometric fusion using Canonical Correlation Analysis (CCA) [36] and its extension, Discriminant Correlation Analysis (DCA) [14], for feature-level fusion
Summary
Biometrics have been shown to be critical to deal with the increasing incidents of fraud challenges in highly secure identity authentication systems. There are a number of other approaches such as Wild et al [35] who proposed to select and keep the most common bit values for each location in the iris feature vectors It has not been used for multispectral fusion yet, it is worth noting a body of work in multimodal biometric fusion using Canonical Correlation Analysis (CCA) [36] and its extension, Discriminant Correlation Analysis (DCA) [14], for feature-level fusion. Considering its advantages when combining the benefits from both concatenation and element-wise multiplication [17], [18], it would be an ideal candidate to learn and model the correlation between multispectral modalities of the same biometric trait in the feature level. To the best of our knowledge, this technique has never been explored for the multispectral fusion task
Sign-in/Register to view highlights & summary 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.
