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.
Similar content being viewed by others
References
Yamada T, Yabuta T (1993) Dynamic system identification using neural networks. IEEE Trans Syst Man Cybern 23(1):204–211
Lu SW, Basar T (1998) Robust nonlinear system identification using neural-network models. IEEE Trans Neural Netw 9(3):407–429
Xianzhong C, Shin KG (1993) Direct control and coordination using neural networks. IEEE Trans Syst Man Cybern 23(3):686–697
Wu S, Wong KYM (1998) Dynamic overload control for distributed call processors using the neural network method. IEEE Trans Neural Netw 9(6):1377–1387
Mazroua AA, Salama MMA et al (1993) PD pattern recognition with neural networks using the multilayer perceptron technique. IEEE Trans Electr Insul 28(6):1082–1089
Srinivasa N, Ahuja N (1993) A topological and temporal correlator network for spatiotemporal pattern learning, recognition, and recall. IEEE Trans Neural Netw 10(2):92–102
Nair SK, Moon J (1997) Data storage channel equalization using neural networks. IEEE Trans Neural Netw 8(5):1037–1048
You C, Hong D (1998) Nonlinear blind equalization schemes using complex-valued multilayer feedforward neural networks. IEEE Trans Neural Netw 9(6):1442–1455
Albus JS (1975) A new approach to manipulator control: the cerebellar model articulation controller (CMAC). Trans ASME J Dyn Syst Meas Contr 220–227
Albus JS (1975) Data storage in the cerebellar model articulation controller (CMAC). Trans ASME J Dyn Syst Meas Contr 228–233
Lee ZJ, Wang YP et al (2004) A genetic algorithm based robust learning credit assignment cerebellar model articulation controller. Appl Soft Comput 4(4):357–367
Su SF, Tao TW et al (2003) Credit assigned CMAC and its application to online learning robust controllers. IEEE Trans Syst Man Cybern B 33(3):202–213
Leu YG, Hong CM et al (2010) Compact cerebellar model articulation controller for ultrasonic motors. Int J Innov Comput Inf Control 6(12):5539–5552
Wu J, Pratt F (1999) Self-organizing CMAC neural networks and adaptive dynamic control. In: Proceedings of IEEE international symposium on intelligent control/intelligent systems and semiotics pp 259–265
Commuri S, Lewis FL (1997) CMAC neural networks for control of nonlinear dynamical systems: structure, stability, and passivity. Automatics 33(4):635–641
Chow MY, Menozzi A (1994) A self-organized CMAC controller. In: Proceedings of IEEE international conference on industrial technology, pp 68–72
Hwang KS, Lin CS (1998) Smooth trajectory tracking of three-link robot: a self-organizing CMAC approach. IEEE Trans Syst Man Cybern B 28(5):680–692
Lee HM, Chen CM et al (2003) A self-organizing HCMAC neural-network classifier. IEEE Trans Neural Netw 14(1):15–27
Reay DS (2003) CMAC and B-spline neural networks applied to switched reluctance motor torque estimation and control. The 29th annual conference of the IEEE industrial electronics society (IECON ‘03) vol 1, pp 323–328
Jou CC (1992) A fuzzy cerebellar model articulation controller. In: Proceedings of IEEE international conference on fuzzy systems, pp 1171–1178
Pedreira CE (2006) Learning vector quantization with training data selection. IEEE Trans Pattern Anal Mach Intell 28(1):157–162
Ang KK, Quek C et al (2003) POPFNN-CRI (S): pseudo outer product based fuzzy neural network using the compositional rule of inference and singleton fuzzifier. IEEE Trans Syst Man Cybern B 33(6):838–849
Chen S, Zhangm D (2004) Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure. IEEE Trans. Systems, Man and Cybernetics, Part B. Cybernetics 34(4):1907–1916
Lin CS, Li CK (1996) A new neural network structure composed of small CMACs. In: Proceedings of IEEE conference neural systems, pp 1777–1783
Lane SH, Militzer J (1992) A comparison of five algorithm for the training of CMAC memories for learning control systems. Int Fed Automat Contr 28(5):1027–1035
Lin CS, Chiang CT (1997) Learning convergence of CMAC technique. IEEE Trans Neural Netw 8(6):1281–1292
Ker JS, Hsu CC et al (1997) A fuzzy CMAC model for color reproduction. Fuzzy Sets Syst 91:53–68
Zhang K, Qian F (2000) Fuzzy CMAC and its application. In: Proceedings of 3rd world congress on intelligent control and automation, pp 944–947
Guo C, Ye Z et al (2002) A hybrid fuzzy cerebellar model articulation controller based autonomous controller. Comput Electr Eng 28(1):1–16
Su SF, Lee ZJ et al (2006) Robust and fast learning for fuzzy cerebellar model articulation controllers. IEEE Trans Syst Man Cybern B Cybern 36(1):203–208
Wu TF, Tsai PS et al (2006) Adaptive fuzzy CMAC control for a class of nonlinear systems with smooth compensation. IEE Proc Control Theory Appl 153(6):647–657
Peng YF, Lin CM (2004) Intelligent hybrid control for uncertain nonlinear systems using a recurrent cerebellar model articulation controller. IEE Proc Control Theory Appl 151(5):589–600
Theocharis JB (2006) A high-order recurrent neuro-fuzzy system with internal dynamics: application to the adaptive noise cancellation. Fuzzy Sets Syst 157(4):471–500
Stavrakoudis DG, Theocharis JB (2007) A recurrent fuzzy neural network for adaptive speech prediction. Proceedings of IEEE international conference systems, man, cybernetics, pp 2056–2061
Terrillon JC, Shirazi MN et al (2000) Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images. IEEE international conference on face and gesture recognition, pp 54–61
Bojic N, Pang KK (2000) Adaptive skin segmentation for head and shoulder video sequence. IEEE conference on visual communications and image processing, pp 704–711
Yang J, Stiefellhagen R et al (1998) Real-time face and facial feature tracking and applications. In: Proceedings of auditory-visual speech process, pp 1–6
Chai D, Bouzerdoum A (2000) A Bayesian approach to skin color classification in YCbCr color space. IEEE TENCON, pp 421–424
Chai D, Ngan KN (1999) Face segmentation using skin color map in video phone applications. IEEE Trans Circuits Syst Video Technol 9(4):551–564
Lin CJ, Chuang HC et al (2006) Face detection in color images using efficient genetic algorithms. Opt Eng 45(4):047201. doi:10.1117/1.2189290
Merz P, Freisleben B (2000) Fitness landscape analysis and genetic algorithms for the quadratic assignment problem. IEEE Trans Evol Comput 4(4):337–352
Karr CL (1991) Design of an adaptive fuzzy logic controller using a genetic algorithm. In: Proceedings of 4th conference on genetic algorithms, pp 450–457
Wang JG, Tai SC et al (2014) Medical diagnosis applications using a novel interactively recurrent self-evolving fuzzy CMAC model. Int Joint Conf Neural Netw 2014:4092–4098
Park J, Sandberg IW (1991) Universal approximation using radial-basis-function networks. Neural Comput 3:246–257
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, JG., Tai, SC. & Lin, CJ. The application of an interactively recurrent self-evolving fuzzy CMAC classifier on face detection in color images. Neural Comput & Applic 29, 201–213 (2018). https://doi.org/10.1007/s00521-016-2551-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2551-x