Title: Improved ELBP descriptors for face recognition
Authors: Shekhar Karanwal; Manoj Diwakar
Addresses: Computer Science and Engineering Department, Graphic Era Deemed to be University, Dehradun, Uttarakhand, India ' Computer Science and Engineering Department, Graphic Era Deemed to be University, Dehradun, Uttarakhand, India
Abstract: In this work, the three novel descriptors are introduced for face recognition (FR) so-called sobel horizontal elliptical local binary pattern (SHELBP), sobel vertical elliptical local binary pattern (SVELBP) and sobel elliptical local binary pattern (SELBP). All three proposed descriptors are the extensions of the work proposed by Nguyen and Caplier (2012). Nguyen and Caplier (2012) proposed three descriptors for FR called as HELBP, VELBP and ELBP. In HELBP and VELBP, the horizontal neighbourhood pixels (aligned elliptically) and vertical neighbourhood pixels (aligned elliptically) are compared with centre pixel to produce their feature sizes and ELBP is the combined histogram extracted from both the descriptors. The performance of these descriptors are not effective under illumination variations (without pre-processing), as it is experimentally proved in this work. To compensate for that sobel operator is applied as image pre-processing before feature extraction is performed. The features extracted from sobel magnitude and directional gradients eliminates this problem very effectively.
Keywords: image pre-processing; feature extraction; dimension reduction and classification.
International Journal of Computational Science and Engineering, 2022 Vol.25 No.2, pp.198 - 210
Received: 27 Oct 2020
Accepted: 13 Apr 2021
Published online: 12 Apr 2022 *