Feature level fusion framework for multimodal biometric system based on CCA with SVM classifier and cosine similarity measure

ABSTRACT

The multimodal biometric system using feature level fusion offers more accurate and reliable recognition performance than the unimodal system. But in practice, feature level fusion is challenging to perform when biometric modalities have heterogeneous and incompatible feature representation and enforce the final decision more confidently. One of the main concerns in the fusion of features is to drive the highly discriminatory representation amongst different biometric modalities. This paper aims to design a framework for an efficient feature level fusion based on canonical correlation analysis (CCA) with a support vector machine (SVM) classifier to get a highly discriminant and affine invariant fused feature vector. The principal component analysis (PCA) + CCA subspace approach is used to achieve dimensionality reduction and feature fusion in a coherent manner, This approach eliminates the need for a complex matcher/classifier design to process a fused feature vector and also reduces computational complexity. The experimental findings for the SDUMLA-HMT multimodal database demonstrate that CCA on the extracted feature sets of iris and fingerprint modalities results in reasonably better multimodal classification accuracy with a substantial reduction in the feature dimensions. Using SVM, we achieved a classification accuracy of 100%. In this paper furthermore, three different distance measures are explored to test the efficacy of the proposed CCA-based feature level fusion approach. The best recognition performance is achieved in terms of an equal error rate (EER) of 0.176% for the cosine similarity measure. We also compared the proposed approach with the match score level fusion method. The proposed feature level fusion approach excels the recognition performance in contrast to the other literature approaches.

KEYWORDS:

• Canonical correlation analysis
• cosine similarity
• feature fusion
• multimodal biometric
• performance evaluation
• support vector machine

Additional information

Notes on contributors

Chetana Kamlaskar

Chetana Kamlaskar is an assistant professor in School of Science and Technology at Y C M Open University, India. She received her doctoral degree PhD (E &TC) from Savitribai Phule Pune University, formerly University of Pune (SPPU), Pune in 2019, postgraduate degree M. Tech (Communication) from IIT Bombay, Mumbai in 1998. She is member of Institution of Engineers (IE) and IETE, Life Member of ISTE. Her current research interests include Multimodal Biometrics, Machine learning, electronics, digital systems, and in eLearning systems.

Aditya Abhyankar

Aditya Abhyankar is currently working as dean, faculty of technology and professor in department of technology, sp pune university. He received his be degree in e & tc from pune university, india in 2001. He received the ms and ph.d. Degrees from clarkson university, ny, usa in 2003 and 2006 respectively. Dr. Abhyankar holds 8 us patents, 14 indian patents, 7 disclosures, 8 technology transfers, 5 us copyrights to his credit. He has also won the number of national and state awards with the likes of iei scientist of the year 2011 award, sir c v raman 2015 award. His research interests include pattern recognition, signal and image processing, wavelet analysis and biometric systems.