Selective attention mechanisms in a vision system based on neural networks

A system for visual recognition derived from a previously developed theoretical framework on the overall organization of the human visual system is proposed. The system operates dynamically by analyzing different parts of the input scene at variable levels of resolution through an attentional spotlight. A constant amount of information is gathered from the scene and a fixed dimension icon is produced, so that a trade-off occurs between the extension of the examined area and the level of resolution at which data are analyzed. The position of the spotlight and its dimensions are determined on the basis of the evolution of the recognition process. The icon is processed by a bottom-up path composed of a five-layer artificial neural network. The results of this net are analyzed by a planning module which determines if recognition has been achieved, or which action to undertake next. A top-down path, including a set of nets trained by the backpropagation algorithm, evaluates the parameters of the next sampling of information. The application of the system to object recognition with varying viewpoint and range from the camera is investigated.

[1]  C. Blakemore,et al.  Vision: The iconic bottleneck and the tenuous link between early visual processing and perception , 1990 .

[2]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[3]  C. Eriksen,et al.  Visual attention within and around the field of focal attention: A zoom lens model , 1986, Perception & psychophysics.

[4]  Peter J. Burt,et al.  Smart sensing within a pyramid vision machine , 1988, Proc. IEEE.

[5]  Peter J. Burt,et al.  Attention mechanisms for vision in a dynamic world , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[6]  K. Nakayama,et al.  Sustained and transient components of focal visual attention , 1989, Vision Research.

[7]  M. Posner,et al.  Attention and the detection of signals. , 1980, Journal of experimental psychology.

[8]  R. Almond.  The therapeutic community. , 1971, Scientific American.

[9]  D. Noton,et al.  Eye movements and visual perception. , 1971, Scientific American.

[10]  G. Sperling,et al.  Dynamics of automatic and controlled visual attention. , 1987, Science.

[11]  R. Desimone,et al.  Selective attention gates visual processing in the extrastriate cortex. , 1985, Science.

[12]  M. Posner,et al.  Orienting of Attention* , 1980, The Quarterly journal of experimental psychology.

[13]  Massimo Bergamasco,et al.  Object characterization and sorting by active touch , 1991, Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91.

[14]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[15]  Paolo Dario,et al.  An approach to disassembly problems in robotics , 1993, Proceedings of 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '93).

[16]  S. Yantis.  On analog movements of visual attention , 1988, Perception & psychophysics.