The security of critical infrastructures is decreasing due to the apparition of new cyber threats against Supervisory Control and Data Acquisition (SCADA) systems. The evolution they have experienced; the use of standard hardware and software components or the increase of interconnected devices in order to reduce costs and improve efficiency, have contributed to this. This work reviews the rese...

Simultaneously detecting an object and determining its pose has become a popular research topic in recent years. Due to the large variances of the object appearance in images, it is critical to capture the discriminative object parts that can provide key information about the object pose. Recent part-based models have obtained state-of-theart results for this task. However, such models either r...

In this paper, various AI programming techniques will be considered in determining which is the most suitable for game playing in a specific domain. The domain is a style of game which involves creating an agent which engages in competition with other agents. In this style of game, a human player will implement a strategy for an agent which will operate within the guidelines of the particular g...

Current peer-to-peer architectures are hardly resistant against unanticipated exceptions such as the failure of single peers. This can be justified by the absence of sophisticated models for exception detection and resolution in peer-to-peer architectures. On the other hand, existing generic models for such self-adaptable architectures are rather theoretical and less suitable for the usage by e...

Text embedded in video sequences is very important to semantic indexing and content-based retrieval system, especially for large scale news collection. However, its detection and extraction is still an open problem due to the variety of its size and the complexity of the backgrounds. In this paper, we propose an approach for automatic Arabic-text localization based on a novel method for text-li...

We describe an algorithm for automatically learning discriminative components of objects with SVM classifiers. It is based on growing image parts by minimizing theoretical bounds on the error probability of an SVM. Component-based face classifiers are then combined in a second stage to yield a hierarchical SVM classifier. Experimental results in face classification show considerable robustness ...

We present a component-based, trainable system for detecting frontal and near-frontal views of faces in still gray images. The system consists of a two-level hierarchy of Support Vector Machine (SVM) classifiers. On the first level, component classifiers independently detect components of a face. On the second level, a single classifier checks if the geometrical configuration of the detected co...

Automated object detection is perhaps the most central task of computer vision and arguably the most difficult one. This paper extends previous work on part-based models by using accurate geometric models both in the learning phase and at detection. In the learning phase manual annotations are used to reduce perspective distortion before learning the part-based models. That training is performe...