Title: Neural Micro-Based Classifier for Face Recognition
Authors: Abdellatief Hussien AbouAli
Volume: 1
Issue: 10
Pages: 32-44
Publication Date: 2017/12/28//
Abstract:
In this study, neural classifier network proposed for face recognition. The proposed network contains four layers: input, micro-classifier, counter, and output. The proposed network based on micro-classifier neurons. The micro-classifier concerns with the classification of two classes of the problem. The proposed network allows incremental learning, more natural than others, the network structure is deterministic, provide confidence factor, and proper generalization is guaranteed. The proposed network was introduced in the context of face recognition methodology however its applications are not confined to it. The methodology included a median filter for noise removal, Legendre moment for feature extraction, and the proposed classifier vehicle. The proposed face recognition methodology was tested using the standard ORL data set. The experimental results of the vehicle showed excellent performance