Hybrid Model for Face Recognition Using Optimized Linear Collaborative Discriminant Regression Classification

Authors

  • T. Syed Akheel, V. Usha Shree, S. Aruna Mastani

DOI:

https://doi.org/10.17762/msea.v71i4.2034

Abstract

Humans can easily solve the difficulty of facial recognition; nevertheless, the fundamental issue is limited memory. The field of automatic facial recognition has advanced quickly, thus far it still confronts challenges like "Ageing, Partial Occlusion, and Facial Expressions," etc. Considering this, the three main stages of pre-processing, feature extraction, and classification are used in this article  to design a novel face recognition framework. The contrast enhancement and RGB to Grey Level Conversion are first carried out in the pre-processing stage. The pre-processed facial image is used to extract the features in the form of shape and texture using AAM. The categorization is then carried out using an improved LCDRC model. The projection matrix is the most important evaluation in the LCDRC. Therefore, it is necessary to optimize the projection matrix to improve recognition precision. The notion of WOA and LA are combined to create the revolutionary hybrid algorithm known as the Combined Whale Lion Model (CWLM), which is used to improve the projection matrix. Recognition rate, False Positive Rate (FPR), and False Discovery Rate (FDR) comparisons with other compared approaches such as LCDRC-WOA, LCDRC-CEWO, and just LCDRC are used to assess the overall performance of the proposed model.

Downloads

Published

2023-03-02

How to Cite

T. Syed Akheel, V. Usha Shree, S. Aruna Mastani. (2023). Hybrid Model for Face Recognition Using Optimized Linear Collaborative Discriminant Regression Classification. Mathematical Statistician and Engineering Applications, 71(4), 10916–10924. https://doi.org/10.17762/msea.v71i4.2034

Issue

Section

Articles