Ibtissam Constantin

Image noise detection in global illumination methods based on FRVM

Global illumination methods based on stochastic techniques provide photo-realistic images. However, they are prone to stochastic perceptual noise that can be reduced by increasing the number of paths as proved by Monte Carlo theory. The problem of finding the required number of paths in order to ensure that human observers cannot perceive any noise is still open. Until now, we do not know precisely which features are considered by the human visual system (HVS) for the evaluation of the image quality. This paper proposes a relevant model to predict which image highlights perceptual noise by using fast relevance vector machine (FRVM). This model can then be used in any progressive stochastic global illumination method in order to find the visual convergence threshold of different parts of any image. A comparative study of this model with experimental psycho-visual scores demonstrates the good consistency between these scores and the model quality measures. The proposed model has also been compared with SVM model and gives competitive performances.

Nonlinear Regularized Wiener Filtering With Kernels: Application in Denoising MEG Data Corrupted by ECG

Magnetoencephalographic and electroencephalographic recordings are often contaminated by artifacts such as eye movements, blinks, and cardiac or muscle activity. These artifacts, whose amplitude may exceed that of brain signals, may severely interfere with the detection and analysis of events of interest. In this paper, we consider a nonlinear approach for cardiac artifacts removal from magnetoencephalographic data, based on Wiener filtering. In recent works, nonlinear Wiener filtering based on reproducing kernel Hilbert spaces and the kernel trick has been proposed. However, the filter parameters are determined by the resolution of a linear system which may be ill conditioned. To deal with this problem, we introduce three kernel methods that provide powerful tools for solving ill-conditioned problems, namely, kernel principal component analysis, kernel partial least squares, and kernel ridge regression. A common feature of these methods is that they regularize the solution by assuming an appropriate prior on the class of possible solutions. We avoid the use of QRS-synchronous averaging techniques, which may induce distortions in brain signals if artifacts are not well detected. Moreover, our approach shows the nonlinear relation between magnetoencephalographic and electrocardiographic signals

Perception of noise in global illumination algorithms based on spiking neural network

This paper proposes a reduced reference quality assessment model based on spiking neural network (SNN) in order to predict which image highlights perceptual noise in unbiased global illumination algorithms. These algorithms provide photo-realistic images by increasing the number of paths as proved by Monte Carlo theory. The objective is to find the number of paths that are required in order to ensure that most of the observers cannot perceive noise in any part of the image. A comparative study of this model with human psycho-visual scores demonstrates the good consistency between these scores and the learning model quality measures. The proposed model that uses a simple architecture composed only from two parallel spike pattern association neurons (SPANs) has been also compared with other learning model like SVM and gives satisfactory performance.

Performance Analysis of Kernel Adaptive Filters based on LMS Algorithm.

The design of adaptive nonlinear filters has sparked a great interest in the machine learning community. The present paper aims to present some recent developments in nonlinear adaptive filtering. We present an in-depth analysis of the performance and complexity of a class of kernel filters based on the recursive least-squares algorithm. A key feature that underlies kernel algorithms is that they map the data in a high-dimensional feature space where linear filtering is performed. The arithmetic operations are carried out in the initial space via evaluation of inner products between pairs of input patterns called kernels. We evaluated the SNR improvement and the convergence speed of kernel-based recursive least-squares filters on two types of applications: time series prediction and cardiac artifacts extraction from magnetoencephalographic data.

Pooling Spike Neural Network for Acceleration of Global Illumination Rendering

The generation of photo-realistic images is a major topic in computer graphics. By using the principles of physical light propagation, images that are indistinguishable from real photographs can be generated. However, this computation is a very time-consuming task. When simulating the real behavior of light, individual images can take hours to be of sufficient quality. This paper proposes a bio-inspired architecture with spiking neurons for acceleration of global illumination rendering. This architecture with functional parts of sparse encoding, learning and decoding consists of a robust convergence measure on blocks. Feature, concatenation and prediction pooling coupled with three pooling operators: convolution, average and standard deviation are used in order to separate noise from signal. The pooling spike neural network (PSNN) represents a non-linear mapping from stochastic noise features of rendering images to their quality visual scores. The system dynamic, that computes a learning parameter for each image based on its level of noise, is a consistent temporal framework where the precise timing of spikes is employed for information processing. The experiments are conducted on a global illumination set which contains diverse image distortions and large number of images with different noise levels. The result of this study is a system composed from only two spike pattern association neurons (SPANs) suitably adopted to the quality assessment task that accurately predict the quality of images with a high agreement with respect to human psycho-visual scores. The proposed spike neural network has also been compared with support vector machine (SVM). The obtained results show that the proposed method gives promising efficiency.

Perception of noise in global illumination based on inductive learning

Global illumination methods are used to simulate lighting in 3D scenes. They provide a progressive convergence to high quality photo-realistic images as proved by Monte Carlo theory. One of the problem of such methods is to determine a stopping condition in order to decide if the computation reaches a satisfactory convergence which allows the process to terminate. In this paper, an inductive learning model for a reduced-reference quality assessment model in large-scale images is proposed as a solution for this problem. One key issue for learning algorithms in global illumination is that they are very efficient to learn perceptual features but are less efficient to learn stochastic noise. Moreover, they need a complete framework with a huge number of images in order to train and evaluate the learning model. These images are very difficult to obtain because of the time required for modeling and scene rendering. The idea is to improve performance by selecting the most pertinent images for the noise perception algorithm. In order to generalize the performance of our approach, experiments are conducted on global illumination scenes, with different precision and noise levels, computed with diffuse and specular rendering. Compared with human psychovisual scores, it can be seen the good consistency between these scores and the learning model quality measures. The proposed model has also been compared with the SVM learning model. The obtained results show that the proposed method is powerful to generalize learning and gives promising efficiency and precision.

Performance analysis of kernel adaptive filters based on RLS algorithm

The design of adaptive nonlinear filters has sparked a great interest in the machine learning community. The present paper aims to present some recent developments in nonlinear adaptive filtering. We present an in-depth analysis of the performance and complexity of a class of kernel filters based on the recursive least-squares algorithm. A key feature that underlies kernel algorithms is that they map the data in a high-dimensional feature space where linear filtering is performed. The arithmetic operations are carried out in the initial space via evaluation of inner products between pairs of input patterns called kernels. We evaluated the SNR improvement and the convergence speed of kernel-based recursive least-squares filters on two types of applications: time series prediction and cardiac artifacts extraction from magnetoencephalographic data.

No-reference quality assessment in global illumination algorithms based on SVM

Global illumination algorithms based on stochastically techniques provide photo-realistic images. However, they are prone to noise that can be reduced by increasing the number of paths as proved by Monte Carlo theory. The problem of finding the number of paths that are required in order to ensure that human observers cannot perceive any stochastic noise is still open. This paper proposes a no-reference quality assessment model based on noise quality indexes and support vector machine (SVM) in order to predict which image highlights perceptual noise. This model can then be used in stochastic global illumination algorithms in order to find the visual convergence threshold of different parts of any image. A comparative study of this model with human psycho-visual scores demonstrates the good consistency between these scores and the learning model quality measures.

Image noise detection in global illumination methods based on fast relevance vector machine

Global illumination methods based on stochastically techniques provide photo-realistic images. However, they are prone to noise that can be reduced by increasing the number of paths as proved by Monte Carlo theory. The problem of finding the number of paths that are required in order to ensure that human observers cannot perceive any noise is still open. In this paper, a novel approach to predict which image highlights perceptual noise is proposed based on Fast Relevance Vector Machine (FRVM). This model can then be used in any progressive stochastic global illumination method in order to find the visual convergence threshold of different parts of any image. A comparative study of this model with experimental psycho-visual scores demonstrates the good consistency between these scores and the model quality measures. The proposed model has been compared also with other learning model like SVM and gives satisfactory performance.