Abdelkader Benyettou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Abdelkader Benyettou has a total of 79 co-authors. Here are the top co-authors by number of shared publications:
- Olivier Lézoray
Université Caen Normandie, ENSICAEN, CNRS, Normandie Univ., GREYC UMR 6072
7 shared publications - Seyyid Ahmed Medjahed
Centre Universitaire Ahmed Zabana
6 shared publications Khalifa Djemal
IBISC Laboratory, Evry Val d'Essonne University, 40, Rue du Pelvoux, 91080 Courcouronnes, France
5 shared publicationsRima Daoudi
IBISC Laboratory, Evry Val d'Essonne University, 40, Rue du Pelvoux, 91080 Courcouronnes, France
4 shared publicationsAbdelhadi Lotfi
Département Tronc Commun, INTTIC Oran, Algérie
3 shared publicationsBoudjelal Meftah
Laboratoire LRSBG, LGeo2E, Université Mustapha Stambouli, Mascara, Algeria
3 shared publications
Latest Publications
- Open Access
- 1 January 2018
- Published by Elsevier in Procedia Computer Science
- Vol. 128, 55-64
Textual Data Selection for Language Modelling in the Scope of Automatic Speech Recognition
- 1 January 2018
- Published by Elsevier in Procedia Computer Science
- Vol. 128, 55-64
Open AccessTextual Data Selection for Language Modelling in the Scope of Automatic Speech Recognition
- 31 August 2017
- Published by Praise Worthy Prize in International Journal on Communications Antenna and Propagation (IRECAP)
- Vol. 7 (4) , 254
On-Line Arabic Characters Recognition Using Enhanced Time Delay Neural Networks
- 31 August 2017
- Published by Praise Worthy Prize in International Journal on Communications Antenna and Propagation (IRECAP)
- Vol. 7 (4) , 254
On-Line Arabic Characters Recognition Using Enhanced Time Delay Neural Networks
- 3 April 2017
- Published by Springer Nature in Cognitive Processing
- Vol. 18 (3) , 315-323
Edge detection based on Hodgkin–Huxley neuron model simulation
In this paper, we propose a spiking neural network model for edge detection in images. The proposed model is biologically inspired by the mechanisms employed by natural vision systems, more specifically by the biologically fulfilled function of simple cells of the human primary visual cortex that are selective for orientation. Several aspects are studied in this model according to three characteristics: feedforward spiking neural structure; conductance-based model of the Hodgkin–Huxley neuron and Gabor receptive fields structure. A visualized map is generated using the firing rate of neurons representing the orientation map of the visual cortex area. We have simulated the proposed model on different images. Successful computer simulation results are obtained. For comparison, we have chosen five methods for edge detection. We finally evaluate and compare the performances of our model toward contour detection using a public dataset of natural images with associated contour ground truths. Experimental results show the ability and high performance of the proposed network model.
- 3 April 2017
- Published by Springer Nature in Cognitive Processing
- Vol. 18 (3) , 315-323
Edge detection based on Hodgkin–Huxley neuron model simulation
In this paper, we propose a spiking neural network model for edge detection in images. The proposed model is biologically inspired by the mechanisms employed by natural vision systems, more specifically by the biologically fulfilled function of simple cells of the human primary visual cortex that are selective for orientation. Several aspects are studied in this model according to three characteristics: feedforward spiking neural structure; conductance-based model of the Hodgkin–Huxley neuron and Gabor receptive fields structure. A visualized map is generated using the firing rate of neurons representing the orientation map of the visual cortex area. We have simulated the proposed model on different images. Successful computer simulation results are obtained. For comparison, we have chosen five methods for edge detection. We finally evaluate and compare the performances of our model toward contour detection using a public dataset of natural images with associated contour ground truths. Experimental results show the ability and high performance of the proposed network model.
- 1 February 2017
- Published by Elsevier in Applied Soft Computing
- Vol. 51, 39-48
Kernel-based learning and feature selection analysis for cancer diagnosis
- 1 February 2017
- Published by Elsevier in Applied Soft Computing
- Vol. 51, 39-48
Kernel-based learning and feature selection analysis for cancer diagnosis
- 31 December 2016
- Published by Praise Worthy Prize in International Review on Computers and Software (IRECOS)
- Vol. 11 (12) , 1209
Arabic Speech Recognition for Connected Words Using HTK: Triphones Expanded to Gmm Based Quran Recognition
- 31 December 2016
- Published by Praise Worthy Prize in International Review on Computers and Software (IRECOS)
- Vol. 11 (12) , 1209
Arabic Speech Recognition for Connected Words Using HTK: Triphones Expanded to Gmm Based Quran Recognition
- Open Access
- 22 December 2016
- Published by Faculty of Electrical Engineering and Computing, Univ. of Zagreb in Journal of Computing and Information Technology
- Vol. 24 (4) , 369-382
Microcanonical Annealing and Threshold Accepting for Parameter Determination and Feature Selection of Support Vector Machines
- 22 December 2016
- Published by Faculty of Electrical Engineering and Computing, Univ. of Zagreb in Journal of Computing and Information Technology
- Vol. 24 (4) , 369-382
Open AccessMicrocanonical Annealing and Threshold Accepting for Parameter Determination and Feature Selection of Support Vector Machines
- Open Access
- 1 December 2016
- Published by Elsevier in The Egyptian Journal of Remote Sensing and Space Sciences
- Vol. 19 (2) , 163-173
A new post-classification and band selection frameworks for hyperspectral image classification
- 1 December 2016
- Published by Elsevier in The Egyptian Journal of Remote Sensing and Space Sciences
- Vol. 19 (2) , 163-173
Open AccessA new post-classification and band selection frameworks for hyperspectral image classification
- 3 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1143-1150
An experimental evaluation of echo state network for colour image segmentation
Image segmentation refers to the process of dividing an image into multiple regions which represent meaningful areas. Image segmentation is an essential step for most image analysis tasks such as object recognition and tracking, pattern recognition, content-based image retrieval, etc. In recent years, a large number of image segmentation algorithms have been developed, but achieving accurate segmentation still remains a challenging task. Recently, reservoir computing (RC) has drawn much attention in machine learning as a new model of recurrent neural networks (RNN). Echo State Network (ESN) represents one efficient realization of RC, which is initially designed to facilitate learning in Recurrent Neural Networks. In this paper we investigate the viability of ESN as feature extractor for pixel classification based colour image segmentation. Extensive experiments are conducted on real world colour image datasets and the global ESN reservoir parameters are varied to identify their operating ranges that allow the use of the reservoir nodes internal activations as new pixel features for the colour image segmentation task. A simple feed forward neural network is used to realize the ESN readout function and classify these new features. The experimental results show that the proposed method achieves high performance image segmentation comparing with state-of-the-art techniques. In addition, a set of empirically derived guidelines for setting the reservoir global parameters are proposed.
- 3 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1143-1150
An experimental evaluation of echo state network for colour image segmentation
Image segmentation refers to the process of dividing an image into multiple regions which represent meaningful areas. Image segmentation is an essential step for most image analysis tasks such as object recognition and tracking, pattern recognition, content-based image retrieval, etc. In recent years, a large number of image segmentation algorithms have been developed, but achieving accurate segmentation still remains a challenging task. Recently, reservoir computing (RC) has drawn much attention in machine learning as a new model of recurrent neural networks (RNN). Echo State Network (ESN) represents one efficient realization of RC, which is initially designed to facilitate learning in Recurrent Neural Networks. In this paper we investigate the viability of ESN as feature extractor for pixel classification based colour image segmentation. Extensive experiments are conducted on real world colour image datasets and the global ESN reservoir parameters are varied to identify their operating ranges that allow the use of the reservoir nodes internal activations as new pixel features for the colour image segmentation task. A simple feed forward neural network is used to realize the ESN readout function and classify these new features. The experimental results show that the proposed method achieves high performance image segmentation comparing with state-of-the-art techniques. In addition, a set of empirically derived guidelines for setting the reservoir global parameters are proposed.
- 31 October 2016
- Published by Praise Worthy Prize in International Review on Computers and Software (IRECOS)
- Vol. 11 (10) , 898
A Set of Features for Text-Independent Writer Identification
- 31 October 2016
- Published by Praise Worthy Prize in International Review on Computers and Software (IRECOS)
- Vol. 11 (10) , 898
A Set of Features for Text-Independent Writer Identification