This book contains the proceedings of the NATO Advanced Research Workshop held in Maratea (Italy), May 5-9, 1986 on Pyramidal Systems for Image Processing and Computer Vision. We had 40 participants from 11 countries playing an active part in the workshop and all the leaders of groups that have produced a prototype pyramid machine or a design for such a machine were present. Within the wide field of parallel architectures for image processing a new area was recently born and is growing healthily: the area of pyramidally structured multiprocessing systems. Essentially, the processors are arranged in planes (from a base to an apex) each one of which is generally a reduced (usually by a power of two) version of the plane underneath: these processors are horizontally interconnected (within a plane) and vertically connected with "fathers" (on top planes) and "children" on the plane below. This arrangement has a number of interesting features, all of which were amply discussed in our Workshop including the cellular array and hypercube versions of pyramids. A number of projects (in different parts of the world) are reported as well as some interesting applications in computer vision, tactile systems and numerical calculations.

Computer vision deals with the problem of manipulating information contained in large quantities of sensory data, where raw data emerge from the transducing 6 7 sensors at rates between 10 to 10 pixels per second. Conventional general purpose computers are unable to achieve the computation rates required to op erate in real time or even in near real time, so massively parallel systems have been used since their conception in this important practical application area. The development of massively parallel computers was initially character ized by efforts to reach a speedup factor equal to the number of processing elements (linear scaling assumption). This behavior pattern can nearly be achieved only when there is a perfect match between the computational struc ture or data structure and the system architecture. The theory of hierarchical modular systems (HMSs) has shown that even a small number of hierarchical levels can sizably increase the effectiveness of very large systems. In fact, in the last decade several hierarchical architectures that support capabilities which can overcome performances gained with the assumption of linear scaling have been proposed. Of these architectures, the most commonly considered in com puter vision is the one based on a very large number of processing elements (PEs) embedded in a pyramidal structure. Pyramidal architectures supply the same image at different resolution lev els, thus ensuring the use of the most appropriate resolution for the operation, task, and image at hand.

Design of intelligent robots is one of the most important endeavors in robotics research today. The key to intelligent robot design lies in sensory systems for robotic control and manipulation. In an unstructural environment, robotic sensing translates measurements and characteristics of the environment and working objects into useful information. A robotic system is usually equipped with a variety of sensors to perform redundant sensing and achieve data fusion. This book contains revised versions of papers presented at a NATO Advanced Research Workshop held in Florida in September 1989 within the activities of the NATO Special Programme on Sensory Systems for Robotic Control. The fundamental issues addressed in this volume were: - Theory and techniques, including knowledge-based systems, geometrical fusion, Boolean fusion, probabilistic fusion, feature-based fusion, error-estimation approach, and Markov process modeling. - General concepts, including microscopic redundancy at the sensory element level, macroscopic redundancy at the sensory system level, parallel redundancy, and standby redundancy. - Implementation and application, including robotic control, sensory technology, robotic assembly, robot fingers, sensory signal processing, sensory system integration, and PAPIA architecture. - Biological analogies, including neural nets, pattern recognition, low-level fusion, and motor learning.

Biological visual systems employ massively parallel processing to perform real-world visual tasks in real time. A key to this remarkable performance seems to be that biological systems construct representations of their visual image data at multiple scales. A Pyramid Framework for Early Vision describes a multiscale, or `pyramid', approach to vision, including its theoretical foundations, a set of pyramid-based modules for image processing, object detection, texture discrimination, contour detection and processing, feature detection and description, and motion detection and tracking. It also shows how these modules can be implemented very efficiently on hypercube-connected processor networks. A Pyramid Framework for Early Vision is intended for both students of vision and vision system designers; it provides a general approach to vision systems design as well as a set of robust, efficient vision modules.

Parallel Computer Vision

Computer vision falls short of human vision in two respects: execution time and intelligent interpretation. This book addresses the question of execution time. It is based on a workshop on specialized processors for real-time image analysis, held as part of the activities of an ESPRIT Basic Research Action, the Working Group on Vision. The aim of the book is to examine the state of the art in vision-oriented computers. Two approaches are distinguished: multiprocessor systems and fine-grain massively parallel computers. The development of fine-grain machines has become more important over the last decade, but one of the main conclusions of the workshop is that this does not imply the replacement of multiprocessor machines. The book is divided into four parts. Part 1 introduces different architectures for vision: associative and pyramid processors as examples of fine-grain machines and a workstation with bus-oriented network topology as an example of a multiprocessor system. Parts 2 and 3 deal with the design and development of dedicated and specialized architectures. Part 4 is mainly devoted to applications, including road segmentation, mobile robot guidance and navigation, reconstruction and identification of 3D objects, and motion estimation.

A machine vision system should be able to analyze images and produce descriptions of what it "sees". The descriptions should capture the aspects of the objects being imaged and be useful for accomplishing some specific tasks. In this volume a number of subjects are discussed. They include theoretical aspects which focus on shape analysis, special architectures, 3-D image decomposition, inspection by machine vision, and others. Applications include geophysical image analysis, robotics, sparse image understanding, biomedical applications. An ample survey of the present industrial applications is also provided.

Scale is a concept the antiquity of which can hardly be traced. Certainly the familiar phenomena that accompany sc ale changes in optical patterns are mentioned in the earliest written records. The most obvious topological changes such as the creation or annihilation of details have been a topic to philosophers, artists and later scientists. This appears to of fascination be the case for all cultures from which extensive written records exist. For th instance, chinese 17 c artist manuals remark that "distant faces have no eyes" . The merging of details is also obvious to many authors, e. g. , Lucretius mentions the fact that distant islands look like a single one. The one topo logical event that is (to the best of my knowledge) mentioned only late (by th John Ruskin in his "Elements of drawing" of the mid 19 c) is the splitting of a blob on blurring. The change of images on a gradual increase of resolu tion has been a recurring theme in the arts (e. g. , the poetic description of the distant armada in Calderon's The Constant Prince) and this "mystery" (as Ruskin calls it) is constantly exploited by painters.

Perceptual processes in humans and machines, investigated and simulated by means of the computational approach, are the subject matter of this volume. Researchers in artificial intelligence, pattern recognition, and psychology discuss aspects of vision, speech understanding, sensory-motor coordination, and their interplay with cognitive and behavioral functionalities. The papers adopt the computational approach as the basic research paradigm. Connectionist models, numerical and statistical techniques, symbolic (logic-based) formalisms, and hybrid representations provide the formal background to the research. Some of the papers were prepared for a workshop held in Trieste, Italy, in October 1992.

This book constitutes the refereed proceedings of the 14th Iberoamerican Congress on Pattern Recognition, CIARP 2009, held in Guadalajara, Mexico, in November 2009. The 64 revised full papers presented together with 44 posters were carefully reviewed and selected from 187 submissions. The papers are organized in topical sections on image coding, processing and analysis; segmentation, analysis of shape and texture; geometric image processing and analysis; analysis of signal, speech and language; document processing and recognition; feature extraction, clustering and classification; statistical pattern recognition; neural networks for pattern recognition; computer vision; video segmentation and tracking; robot vision; intelligent remote sensing, imagery research and discovery techniques; intelligent computing for remote sensing imagery; as well as intelligent fusion and classification techniques.