Biometric association using transfer subspace learning
Authors:
- 9 February 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1384-1387
Abstract
Different biometrics studies related to face, fingerprint, hand geometry, palmprint, and iris has been taken place in recent past. In this paper two biometrics, face and fingerprint are considered and associated with each other using transfer subspace learning. Transfer subspace learning can share common subspace even if domains are different by minimizing the distance between their probability distribution. Locality preserving projections is used as objective function to discriminate between source domains. This works linearly and preserves the local geometry of the structure by obtaining the subspace spanned by smallest eigenvectors of local covariance matrix. Proposed framework will be very useful in the forensic applications. Though the accuracy of this system is not very high it will help to separate the most probable suspects.Keywords
This publication has 11 references indexed in Scilit:
- Understanding Kin Relationships in a PhotoIEEE Transactions on Multimedia, 2012
- Social image annotation via cross-domain subspace learningMultimedia Tools and Applications, 2010
- Cross-database age estimation based on transfer learning2010
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Bregman Divergence-Based Regularization for Transfer Subspace LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Multimodal Biometric System Using Rank-Level Fusion ApproachIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2009
- Artificial neural network based automatic face parts prediction system from only fingerprints2009
- Integrating Palmprint and Fingerprint for Identity Verification2009
- Boosting for transfer learning2007
- Transfer Learning in Sign language2007