| This book presents an approach to the construction of a visual system, which is behaviorally, computationally and neurally motivated. The goal is to characterize the process of visual categorization and to find a suitable representation format that can successfully deal with the structural variability existent within visual categories. The book reviews past and existent theories of visual object and shape recognition in the fields of computer vision, neuroscience and psychology. The entire range of computations is discussed, as are region-based approaches and are modeled with wave-propagating networks. A completely novel shape recognition architecture is proposed that can recognize simple shapes under various degraded conditions. It is discussed how such networks can be used for constructing basic-level object representations. It is envisioned how those networks can be implemented using the method of neuromorphic engineering.
My driving intuition is that visual category representations need to be loose in order to be able to cope with the visual structural variability existent within categories and that these loose representations are somehow expressed as neural activity in the nervous system. I regard such loose representations as the cause for experiencing visual illusions and the cause for many of those effects discovered in attentional experiments. During my effort to find such loose representations, I have made sometimes unexpected experiences that forced me to continuously rethink my approach and to abandon or turn over some of my initially strongly believed viewpoints. The book therefore represents somewhat the odyssey through different attempts: At the beginning I pursued a typical structural description scheme (chapter 5), which eventually has turned into a search of a mixture of shape description methods using wave-propagating networks (chapter 10). What the exact nature of these representations should look like, is yet still unclear to me, but one would simply work towards it by constructing, testing and refining different architectures. I regard the construction of a visual system therefore as a stepwise process, very similar to the invention and evolutionary-like refinement of other technical systems like the automobile, airplane, rocket or computer. In order to build a visual system that processes with the same or similar efficiency, I believe that it is worth to understand how the human visual system may achieve this performance on a behavioral, on an architectural as well as on a network level. To emulate the envisioned mechanisms and processes with the same swiftness, it may be necessary to employ a substrate that can cope with the intensity of the demanded computations, for example the here mentioned neuromorphic analog circuits (chapter 4). |