Multi-Resolution Discrete Cosine Transform Fusion Technique Face Recognition Model

This work presents a Multi-Resolution Discrete Cosine Transform (MDCT) fusion technique Fusion Feature-Level Face Recognition Model (FFLFRM) comprising face detection, feature extraction, fusion, and classification. It detects core facial characteristics as well local global features utilizing Local Binary Pattern (LBP) Principal Component Analysis (PCA) extraction. MDCT was applied, followed by Artificial Neural Network (ANN) testing used 10,000 faces derived from the Olivetti Research Laboratory (ORL) library. performance evaluated in comparison with three state-of-the-art models depending on Frequency Partition (FP), Laplacian Pyramid (LP) Covariance Intersection (CI) techniques, terms of image (low-resolution issues occlusion) (pose, expression per se relation to illumination). The MDCT-based model yielded promising recognition results, 97.70% accuracy demonstrating effectiveness robustness for challenges. Furthermore, this proved that method proposed FFLFRM is simpler, faster, more accurate than Fourier (DFT), Fast (FFT) Wavelet (DWT). As it an effective real-life applications.