Interest point based face recognition using adaptive neuro fuzzy inference system

In this paper, an efficient face recognition method using AGA and ANFIS-ABC has been proposed. At first stage, the face images gathered from the database are preprocessed. At Second stage, an interest point which is used to improve the detection rate consequently. The parameters used in the interest...

Full description

Saved in:
Bibliographic Details
Published in:Multimedia tools and applications 2019-08, Vol.78 (16), p.22691-22710
Main Author: Rejeesh, M R
Format: Article
Language:English
Subjects:
Adaptive algorithms
Adaptive systems
Artificial neural networks
Computer Communication Networks
Computer Science
Data Structures and Information Theory
Face recognition
Facial recognition technology
False alarms
Feature extraction
Fuzzy logic
Fuzzy systems
Genetic algorithms
Image detection
Multimedia Information Systems
Process parameters
Search algorithms
Special Purpose and Application-Based Systems
Swarm intelligence
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, an efficient face recognition method using AGA and ANFIS-ABC has been proposed. At first stage, the face images gathered from the database are preprocessed. At Second stage, an interest point which is used to improve the detection rate consequently. The parameters used in the interest point determination are optimized using the Adaptive Genetic Algorithm. Finally using ANFIS, face images are classified by using extracted features. During the training process, the parameters of ANFIS are optimized using Artificial Bee Colony Algorithm (ABC) in order to improve the accuracy. The performance of the proposed ANFIS-ABC technique is evaluated using an ORL database with 400 images of 40 individuals, YALE-B database with 165 images of 15 individuals and finally with real time video the detection rate and false alarm rate is compared with proposed and existing methods to prove the system efficiency.
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-019-7577-5