Efficient face recognition using frequency distribution curve matching
Document Type
Article
Publication Date
12-1-2012
Abstract
To develop an accurate and efficient face recognition system, a technique is proposed that preserves holistic as well as local facial details. It employs the cumulative frequency distribution curve (FDC) of the grey levels and their standard variance. Based on the FDC, a reduced space profile is produced, which is composed of three distinct segments. Each segment has its own associated error value defined in the range (0, 1). A decision is made by evaluating error values between the training and testing data sets independently for each segment in the FDC. A face is recognised accurately if there is conformance in all of the three segments; that is, the relevant error conditions are met simultaneously in all the segments. With one-shot training, the proposed technique is not only faster but also provides 14, 1.9 and 1.7% improvement in accuracy for the Yale, Olivetti Research Laboratory and pose, illumination and expression databases compared with other widely used face recognition techniques. © The Institution of Engineering and Technology 2012.
Identifier
84880012921 (Scopus)
Publication Title
Iet Image Processing
External Full Text Location
https://doi.org/10.1049/iet-ipr.2011.0565
ISSN
17519659
First Page
1161
Last Page
1196
Issue
8
Volume
6
Recommended Citation
Sajid, I. A.; Ziavras, S. G.; and Ahmed, M. M., "Efficient face recognition using frequency distribution curve matching" (2012). Faculty Publications. 17979.
https://digitalcommons.njit.edu/fac_pubs/17979
