Modern image processing techniques are based on multiresolution geometrical methods of image representation. These methods are efficient in sparse approximation of digital images. There is a wide family of functions called simply ‘X-lets’, and these methods can be divided into two groups: the adaptive and the nonadaptive. This book is devoted to the adaptive methods of image approximation, especially to multismoothlets. Besides multismoothlets, several other new ideas are also covered. Current literature considers the black and white images with smooth horizon function as the model for sparse approximation but here, the class of blurred multihorizon is introduced, which is then used in the approximation of images with multiedges. Additionally, the semi-anisotropic model of multiedge representation, the introduction of the shift invariant multismoothlet transform and sliding multismoothlets are also covered. Geometrical Multiresolution Adaptive Transforms should be accessible to both mathematicians and computer scientists. It is suitable as a professional reference for students, researchers and engineers, containing many open problems and will be an excellent starting point for those who are beginning new research in the area or who want to use geometrical multiresolution adaptive methods in image processing, analysis or compression.

This volume is a post-event proceedings volume and contains selected papers based on presentations given, and vivid discussions held, during two workshops held in Taormina in 2003 and 2004. The 30 thoroughly revised papers presented are organized in the following topical sections: recognition of specific objects, recognition of object categories, recognition of object categories with geometric relations, and joint recognition and segmentation.

This book shows how machine learning can detect moving objects in a digital video stream. The authors present different background subtraction approaches, foreground segmentation, and object tracking approaches to accomplish this. They also propose an algorithm that considers a multimodal background subtraction approach that can handle a dynamic background and different constraints. The authors show how the proposed algorithm is able to detect and track 2D & 3D objects in monocular sequences for both indoor and outdoor surveillance environments and at the same time, also able to work satisfactorily in a dynamic background and with challenging constraints. In addition, the shows how the proposed algorithm makes use of parameter optimization and adaptive threshold techniques as intrinsic improvements of the Gaussian Mixture Model. The presented system in the book is also able to handle partial occlusion during object detection and tracking. All the presented work and evaluations were carried out in offline processing with the computation done by a single laptop computer with MATLAB serving as software environment.

This book constitutes the refereed proceedings of the 16th Australian Conference on Artificial Intelligence, AI 2003, held in Perth, Australia in December 2003. The 87 revised full papers presented together with 4 keynote papers were carefully reviewed and selected from 179 submissions. The papers are organized in topical sections on ontologies, problem solving, knowledge discovery and data mining, expert systems, neural network applications, belief revision and theorem proving, reasoning and logic, machine learning, AI applications, neural computing, intelligent agents, computer vision, medical applications, machine learning and language, AI and business, soft computing, language understanding, and theory.