Abstract

AbstractLiterature reveals that by the fusion of global and local descriptors more finer results are earned than either of them alone. Motivated by this, the proposed work introduces the novel fusion scheme by amalgamating the features of three effective descriptors, i.e., PCA, LBP and LPQ. PCA is availed as the global feature extractor and the local feature extraction are carried out by LBP and LPQ. This fusion scheme is termed as the PCA + LBP + LPQ. Prior to amalgamation, z-score normalization is carried out on the respective descriptor. The LBP and LPQ features are attained region wise from corresponding map images. The amalgamated size is on the bigger side; therefore, PCA services are exploited again for compact size. For matching SVMs are availed, and four datasets deployed are ORL, GT, JAFFE and Faces94. The PCA + LBP + LPQ pulls of superb recognition rates than either of PCA, LBP and LPQ. It also overshadow the numerous literature-based techniques.KeywordsPrincipal component analysis (PCA)Local binary pattern (LBP)Local phase quantization (LPQ)Support vector machines (SVMs)

Full Text
Paper version not known

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 call

Disclaimer: 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.