Ali Douik

Cereal varieties classification using wavelet techniques combined to multi-layer neural networks

This paper presents a new classification method of the various cereal grains varieties. The first phase consists in generating primitives using the wavelet techniques. These primitives are tested by a statistical study and validation tests to extract the deterministic parameters. The second part consists in developing a neuronal classifier designed using the multilayer neural networks to classify the three grain classes (hard wheat, tender wheat and barley). The third part consists to identify the mitadin grains from hard wheat and to classify them in three categories of mitadinage.

Texture descriptor based on local combination adaptive ternary pattern

Material recognition has several applications, such as image retrieval, object recognition and robotic manipulation. To make the material classification more suitable for real-world applications, it is fundamental to satisfy two characteristics: robustness to scale and to pose variations. In this study, the authors propose a novel discriminant descriptor for texture classification based on a new operator called local combination adaptive ternary pattern (LCATP) descriptor used to encode both colour and local information. They start by building the LCATP descriptor using a combination of three different adaptive thresholding techniques. Moreover, they present a novel operator, mean histogram (MH), used jointly with the LCATP in order to incorporate colour information into the descriptor. This approach is then extended to four different colour spaces: LC 1 C 2, I 1 I 2 I 3, LSHuv and O 1 O 2 O 3. The final descriptor, LCATP fusion (LCATP_F), is produced by fusing the basic histogram (H) and MH extracted from the different colour spaces. Finally, the LCATP_F descriptor properties, such as the robustness to scale and pose changes are evaluated using the challenging KTH-textures under varying illumination, pose and scale (TIPS2b) dataset along with the least squares support vector machines classifier. The obtained experimental results, using the LCATP_F descriptor, show a significant improvement with respect to the state-of-the-art results.

FPGA implementation of filtered image using 2D Gaussian filter

Image filtering is one of the very useful techniques in image processing and computer vision. It is used to eliminate useless details and noise from an image. In this paper, a hardware implementation of image filtered using 2D Gaussian Filter will be present. The Gaussian filter architecture will be described using a different way to implement convolution module. Thus, multiplication is in the heart of convolution module, for this reason, three different ways to implement multiplication operations will be presented. The first way is done using the standard method. The second way uses Field Programmable Gate Array (FPGA) features Digital Signal Processor (DSP) to ensure and make fast the scalability of the effective FPGA resource and then to speed up calculation. The third way uses real multiplier for more precision and a the maximum uses of FPGA resources. In this paper, we compare the image quality of hardware (VHDL) and software (MATLAB) implementation using the Peak Signal-to-Noise Ratio (PSNR). Also, the FPGA resource usage for different sizes of Gaussian kernel will be presented in order to provide a comparison between fixed-point and floating point implementations.

Non-Rigid Objects Recognition: Automatic Human Action Recognition in Video Sequences

Non-rigid objects recognition is an important problem in video analysis and understanding. It is nevertheless a challenging task to achieve due to the properties carried out by the nonrigid objects, and is more complicated by camera motion as well as background variation. Human body recognition in video sequences is the best application of the non-rigid objects recognition due to the large capacities of the human body in doing actions and poses. These difficulties prohibit practical attempts toward conceiving a robust global model for each action class. Human body recognition is highly interesting for a variety of applications: detecting relevant activities in surveillance video, summarizing and indexing video sequences. It relies, however, on the interpretation of the body movements and classifies them in different events.

Video Saliency Using Supervoxels

Physiology and neural systems researchers revealed that the visual system is attracted by some parts of an image more than others. Different computational models were developed to simulate the visual system. In this paper we propose a video saliency model that helps to predict and detect the regions of interest in each video frame. We use a supervoxel segmentation as an indicator of dynamic objects. Based on the observation that dynamic objects attract attention when an observer watches a video sequence, supervoxel segmentation provides a first estimation for what belongs to foreground and background. Then, a saliency score is attributed to each supervoxel according to its motion distinctiveness. Experiments over two benchmark datasets, using several evaluation metrics have shown that our proposed method outperforms five saliency detection methods.

Detecting and Recognizing Salient Object in Videos

Saliency detection has been an interesting research field. Some researchers consider it as a segmentation problem some others treat it differently. In this paper, we propose a novel video saliency framework that detects and recognizes the object of interest.

Modelling and predictive control of an inverted pendulum system by MLD approach: multivariable case

This paper deals with a class of hybrid systems that is presented by mixed logical dynamical (MLD) formalism. This approach is well-adapted to hybrid systems, particularly because of its ability not only to model systems involving continuous and discrete dynamics under constraints, but also to address several issues such as model predictive control (MPC) of this class of systems. This approach will be illustrated by the multivariable modelling of the inverted pendulum system. Therefore, the resultant system is well-posed for MPC strategy. Simulations were effected using the HYSDEL compiler to illustrate the efficiency of this formalism.

Explicit model-predictiv e control of hybrid dynamical systems: Application to a two-tank system

In this paper, we consider the solution of explicit model predictive control problem for piecewise affine systems in order to compare the results for the quadratic criterion and the linear one. Two issues are addressed: First, we start by computing the solution of the considered problem and determine the structure of the control law. Thereafter, we aim to reduce the complexity of the obtained control law to improve system performance in terms of number of polyhedral regions and computation time.

New matching method for human body tracking

In this paper we present a new method for interest points matching to realize human body tracking in video sequences. The developed algorithm combines direct and indirect similarity measures evaluated when applying luminosity variation and motion blur noises. This new approach considers different matching constraints such as: cross-matching, uniqueness constraint and interest points appearances and disappearances between consecutive images. The algorithm was evaluated on two different datasets and leads to high values of Good Tracking Rate.

Synthesis of spatio-temporal interest point detectors: Harris 3D, MoSIFT and SURF-MHI

The purpose of this paper is to evaluate and compare different spatio-temporal interest points (STIP) detectors which are considered as extensions of the most common interest points (IP) detectors in 2D images to 3D space-time features: Harris 3D, Motion Scale Invariant Feature Transform (MoSIFT) and Speeded Up Robust Features Motion History Image (SURF-MHI). This paper uses the criteria of repeatability and time execution to evaluate the approaches. We proposed to find matching using the approximation method of nearest neighbors. We investigate the performance of these methods for illumination variation, scale variation, rotation and compression were applied over three dataset. All the experiments were implemented in Matlab computing environment.