At the fascinating frontiers of neurobiology, mathematics and psychophysics, this book addresses the problem of human and computer vision on the basis of cognitive modeling. After recalling the physics of light and its transformation through media and optics, H rault presents the principles of the primate's visual system in terms of anatomy and functionality. Then, the neuronal circuitry of the retina is analyzed in terms of spatio-temporal filtering. This basic model is extended to the concept of neuromorphic circuits for motion processing and to the processing of color in the retina. For more in-depth studies, the adaptive non-linear properties of the photoreceptors and of ganglion cells are addressed, exhibiting all the power of the retinal pre- processing of images as a system of information cleaning suitable for further cortical processing. As a target of retinal information, the primary visual area is presented as a bank of filters able to extract valuable descriptors of images, suitable for categorization and recognition and also for local information extraction such as saliency and perspective. All along the book, many comparisons between the models and human perception are discussed as well as detailed applications to computer vision.

This volume contains the collected papers of the NATO Advanced Research Workshop on neurocomputing held in Les Arcs in February 1989. Various fields in neurocomputing are covered, including: - new or improved neural network algorithms: product units, recurrent multilayer networks, Boltzmann machines, Kohonen maps, growth algorithms; - topics in neural architectures: VLSI circuits, VLSI neurons, dedicated processors; - applications in speech processing: coding, link with hidden Markov Models (HMM), recognition, compression; - applications in image processing: recognition of digits, wind maps, mammographic images, compression; - models in neurobiology: cortical columns, posture, movement coordination. The book can be read at various levels. Newcomers will find in it a useful introduction to the field through the major papers, by leading scientists, and the collected bibliography at the end of the volume. Specialists will learn about some of the more advanced applications, architectures, chip designs and new algorithms. The book will interest all neural network scientists who wish to know what is happening in Europe.