Efficient human face recognition in real-life applications using the discrete wavelet transformation (HFRDWT)

Human Face receives major attention and acquires most of the efforts of the research and studies of Machine Learning in detection and recognition. In real-life applications, the problem of quick and rapid recognition of the Human Face is always challenging researchers to come out with powerful and r...

Full description

Saved in:
Bibliographic Details
Published in:Multimedia tools and applications 2023-12, Vol.83 (20), p.59121-59142
Main Authors: Eragi, Saddam M., BenSaid, Fatma, Alimi, Adel M.
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Approximation
Artificial neural networks
Biometrics
Computer Communication Networks
Computer Science
Data Structures and Information Theory
Datasets
Deep learning
Discrete Wavelet Transform
Face recognition
Facial recognition technology
Image resolution
Machine learning
Multimedia
Multimedia Information Systems
Neural networks
Special Purpose and Application-Based Systems
Track 3: Biometrics and HCI
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Human Face receives major attention and acquires most of the efforts of the research and studies of Machine Learning in detection and recognition. In real-life applications, the problem of quick and rapid recognition of the Human Face is always challenging researchers to come out with powerful and reliable techniques. In this paper, we proposed a new human face recognition system using the Discrete Wavelet Transformation named HFRDWT. The proposed system showed that the use of Wavelet Transformation along with the Convolutional Neural Network to represent the features of an image had significantly reduced the face recognition time, which makes it useful in real-life areas, especially in public and crowded places. The Approximation coefficient of the Discrete Wavelet Transformation played the dominant role in our system by reducing the raw image resolution to a quarter while maintaining the high level of accuracy rate that the raw image had. Results on ORL, Japanese Female Facial Expression, extended Cohn-Kanade, Labeled Faces in the Wild datasets, and our new Sudanese Labeled Faces in the Wild dataset showed that our system obtained the least recognition timing (average of 24 milliseconds for training and 8 milliseconds for testing) and acceptable high recognition rate (average of 98%) compared to the other systems.
ISSN:1573-7721
1380-7501
1573-7721
DOI:10.1007/s11042-023-17232-6