Home / Current Issue / Paper 1715017
Face Recognition Using Local Pattern Based on Vector Quantization with RBF-SVM
Subject area: Science,Engineering and Technology · Area of research: Computer Vision/Face Recognition
DOI: https://doi.org/10.64388/IREV9I9-1715017
Abstract
Face recognition remains challenging due to variations in illumination, pose, expression, and noise. This paper proposes an efficient face recognition framework that integrates local pattern–based feature extraction with Vector Quantization (VQ) and a Radial Basis Function Support Vector Machine (RBF-SVM). Local pattern descriptors capture fine-grained texture and spatial information, providing robustness to local variations. To reduce feature dimensionality and improve computational efficiency, the extracted features are encoded using vector quantization to form compact and discriminative representations. Classification is performed using an RBF-SVM, which effectively models non-linear decision boundaries. Experimental results demonstrate that the proposed approach achieves high recognition accuracy with low computational cost, outperforming conventional local pattern–based methods under varying illumination and expression conditions.
Keywords
Face Recognition, RBF-SVM, Texture Descriptor, Vector Quantization
How to cite this paper
@article{1715017,
author = {Dr. A. Srikrishna, P. Bindu Sri, M. Ramgopal, J. Aravind, Ch. Devi Sri Krithi},
title = {Face Recognition Using Local Pattern Based on Vector Quantization with RBF-SVM},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {9},
pages = {806-815},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1715017.pdf},
abstract = {Face recognition remains challenging due to variations in illumination, pose, expression, and noise. This paper proposes an efficient face recognition framework that integrates local pattern–based feature extraction with Vector Quantization (VQ) and a Radial Basis Function Support Vector Machine (RBF-SVM). Local pattern descriptors capture fine-grained texture and spatial information, providing robustness to local variations. To reduce feature dimensionality and improve computational efficiency, the extracted features are encoded using vector quantization to form compact and discriminative representations. Classification is performed using an RBF-SVM, which effectively models non-linear decision boundaries. Experimental results demonstrate that the proposed approach achieves high recognition accuracy with low computational cost, outperforming conventional local pattern–based methods under varying illumination and expression conditions.},
keywords = {Face Recognition, RBF-SVM, Texture Descriptor, Vector Quantization},
month = {March},
doi = {https://doi.org/10.64388/IREV9I9-1715017}
}