A new integrated approach to human face recognition and expression identification based on Gray Level Co-occurrence Matrix (GLCM) technique that will be useful for Human Face Recognition and Feature Extraction system based on Local Ternary Pattern (LTP) for expression identification was introduced. It applies GLCM operation to extract the features of facial images to different classes for the purpose of image classification and verification by Kernel Principal Component analysis (KPCA) technique and “expression identification” by extracting the features using LTP method and classifies uses SVM technique. In the proposed method, Gray Level Co-occurrence is used to extract the texture features of an image with different attribute levels, and then the Euclidean distance classifier is used to match the top ten images from all the database images, and finally, KPCA method of the Eigen face is applied only on the ten sorted instead of all the database images which in turn reduces the computational time, and then the LTP features is extracted for the identification of the facial expression with improved recognition rate. The performance Evaluation is done by calculating the False Acceptance Rate (FAR), and the False Rejection Rate (FRR) and compared with the existing methods.
Key words: Face recognition, Gray Level Co-occurrence Matrix, Kernel Principal Component Analysis, false acceptance rate, false rejection rate.
Copyright © 2022 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0