The application of an interactively recurrent self-evolving fuzzy CMAC classifier on face detection in color images

Jyun Guo Wang, Shen Chuan Tai, Cheng Jian Lin

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

This study proposes an interactively recurrent self-evolving fuzzy cerebellar model articulation controller (IRSFCMAC) classifier to solve face detection problems. The learning methods of the proposed classifier are based on simultaneous structure and parameter learning. The structure learning is used to decide the proper input space partition, while the parameter learning is based on gradient descent method. The online structure learning does not need to set any initial structure in advance. In other words, the online structure learning algorithm enables the network along of the problem to efficiently identify the required network structure. The advantages of our proposed IRSFCMAC classifier include (1) using a non-constant differentiable Gaussian basis function to model the hypercube structure; (2) applying an interactively recurrent structure to serve as external loops and internal feedbacks by feeding the hypercube cell (rule) firing strength to itself and other hypercube cells (rules); and (3) requiring fewer computing memory. Finally, experimental results show that the proposed IRSFCMAC classifier is a more adaptive and effective face detection than the other classifiers.

Original languageEnglish
Pages (from-to)201-213
Number of pages13
JournalNeural Computing and Applications
Volume29
Issue number6
DOIs
Publication statusPublished - 2018 Mar 1

Fingerprint

Face recognition
Classifiers
Color
Controllers
Learning algorithms
Feedback
Data storage equipment

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

@article{9863c8f31f394eccbbac0687df08400a,
title = "The application of an interactively recurrent self-evolving fuzzy CMAC classifier on face detection in color images",
abstract = "This study proposes an interactively recurrent self-evolving fuzzy cerebellar model articulation controller (IRSFCMAC) classifier to solve face detection problems. The learning methods of the proposed classifier are based on simultaneous structure and parameter learning. The structure learning is used to decide the proper input space partition, while the parameter learning is based on gradient descent method. The online structure learning does not need to set any initial structure in advance. In other words, the online structure learning algorithm enables the network along of the problem to efficiently identify the required network structure. The advantages of our proposed IRSFCMAC classifier include (1) using a non-constant differentiable Gaussian basis function to model the hypercube structure; (2) applying an interactively recurrent structure to serve as external loops and internal feedbacks by feeding the hypercube cell (rule) firing strength to itself and other hypercube cells (rules); and (3) requiring fewer computing memory. Finally, experimental results show that the proposed IRSFCMAC classifier is a more adaptive and effective face detection than the other classifiers.",
author = "Wang, {Jyun Guo} and Tai, {Shen Chuan} and Lin, {Cheng Jian}",
year = "2018",
month = "3",
day = "1",
doi = "10.1007/s00521-016-2551-x",
language = "English",
volume = "29",
pages = "201--213",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",
number = "6",

}

The application of an interactively recurrent self-evolving fuzzy CMAC classifier on face detection in color images. / Wang, Jyun Guo; Tai, Shen Chuan; Lin, Cheng Jian.

In: Neural Computing and Applications, Vol. 29, No. 6, 01.03.2018, p. 201-213.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The application of an interactively recurrent self-evolving fuzzy CMAC classifier on face detection in color images

AU - Wang, Jyun Guo

AU - Tai, Shen Chuan

AU - Lin, Cheng Jian

PY - 2018/3/1

Y1 - 2018/3/1

N2 - This study proposes an interactively recurrent self-evolving fuzzy cerebellar model articulation controller (IRSFCMAC) classifier to solve face detection problems. The learning methods of the proposed classifier are based on simultaneous structure and parameter learning. The structure learning is used to decide the proper input space partition, while the parameter learning is based on gradient descent method. The online structure learning does not need to set any initial structure in advance. In other words, the online structure learning algorithm enables the network along of the problem to efficiently identify the required network structure. The advantages of our proposed IRSFCMAC classifier include (1) using a non-constant differentiable Gaussian basis function to model the hypercube structure; (2) applying an interactively recurrent structure to serve as external loops and internal feedbacks by feeding the hypercube cell (rule) firing strength to itself and other hypercube cells (rules); and (3) requiring fewer computing memory. Finally, experimental results show that the proposed IRSFCMAC classifier is a more adaptive and effective face detection than the other classifiers.

AB - This study proposes an interactively recurrent self-evolving fuzzy cerebellar model articulation controller (IRSFCMAC) classifier to solve face detection problems. The learning methods of the proposed classifier are based on simultaneous structure and parameter learning. The structure learning is used to decide the proper input space partition, while the parameter learning is based on gradient descent method. The online structure learning does not need to set any initial structure in advance. In other words, the online structure learning algorithm enables the network along of the problem to efficiently identify the required network structure. The advantages of our proposed IRSFCMAC classifier include (1) using a non-constant differentiable Gaussian basis function to model the hypercube structure; (2) applying an interactively recurrent structure to serve as external loops and internal feedbacks by feeding the hypercube cell (rule) firing strength to itself and other hypercube cells (rules); and (3) requiring fewer computing memory. Finally, experimental results show that the proposed IRSFCMAC classifier is a more adaptive and effective face detection than the other classifiers.

UR - http://www.scopus.com/inward/record.url?scp=84982271332&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84982271332&partnerID=8YFLogxK

U2 - 10.1007/s00521-016-2551-x

DO - 10.1007/s00521-016-2551-x

M3 - Article

AN - SCOPUS:84982271332

VL - 29

SP - 201

EP - 213

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 6

ER -