Youssef Harkouss

Learn More
This paper presents a new image encryption technique based on neural chaotic generator. This encryption technique includes two main operations, permutation at pixel level and masking and permutation at bit level. The chaotic generator used in the encryption of image is perturbed by a new technique done by artificial neural network. Simulations show that the(More)
The paper investigates adaptive equalization of nonlinear time varying digital communication channel. An architecture of equalization was proposed based on the Bayesian theory (R. Assaf et al., 2005) where an implementation by radial basis function neural network (RBFNN) was accomplished. We treated the equalization of binary transmission signal through(More)
This paper presents a new algorithm for constructing and training wavelet neural network. This algorithm is based on the variation of the number of hidden neurons dynamically during the training process. The suggested method determines the optimal number of the hidden neurons and solves the optimization problem of wavelet neural network structure. The(More)
In this paper, we propose a new implementation of chaotic generator using artificial neural network. Neural network can act as an efficient source of perturbation in the chaotic generator which increases the cycle's length, and thus avoid the dynamical degradation due to the used finite dimensional space. On the other hand, the use of neural network(More)
Segmentation of image is used from a long time in medical image applications and its study is increased for enhanced the medical diagnosis. This paper concerns a deformable segmentation method for abnormal cells detection by using an improved Level set model which is solved several problems and disadvantages of others segmentation technique. Our approach(More)
The paper presents an adaptive RBFNNE (Radial Basis Function Neural Network Equalizer) of nonlinear time-varying UMTS channel; The architecture of the RBFNNE implements the Bayesian decision function. Centers of hidden layer neurons, equal to the channel states, are determined by an unsupervised classification algorithm based on the Rival Penalized(More)
In this paper, we propose a new neural dynamic block cipher based on a combination between Artificial Neural Network (ANN) and an efficient nonlinear function. A dynamic construction method of synaptic weight matrices is achieved by updating the weight matrices after each validate time and the problem of reversibility is resolved. The main advantage of(More)
Image segmentation is a widely used in medical imaging applications by detecting anatomical structures and regions of interest. This paper concerns a survey of numerous segmentation model used in biomedical field. We organized segmentation techniques by four approaches, namely, thresholding, edge-based, region-based and snake. These techniques have been(More)