Title :
Data and model driven foveation
Author :
Califano, Andrea ; Kjeldsen, Rick ; Bolle, Ruud M.
Author_Institution :
IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Abstract :
A general framework for multiresolution visual recognition is introduced. The input is processed simultaneously at a coarse resolution throughout the image and at finer resolution within a small window. An approach for controlling the movement of the high-resolution window is described which allows for the unification of a variety of data and model-driven behavioral paradigms. Three modes have been implemented, one based on large unexplained areas in the data, one on conflicts in the object-model database, and one on a 2D space-filling algorithm. It is argued that this kind of multiresolution processing not only is useful in limiting the computational time, but also can be a deciding factor in making the entire vision problem a tractable and stable one. To demonstrate the approach, a class of 3D surface textures is introduced as a feature for recognition in the system considered. Surface texture recognition typically requires higher-resolution processing than required for the extraction of the underlying surface. As an example, surface texture is used to discriminate between a ping-pong ball and a golf ball
Keywords :
computerised pattern recognition; computerised picture processing; 2D space-filling algorithm; 3D surface textures; coarse resolution; computational time; database conflicts; fine resolution; foveation; golf ball; high-resolution window; multiresolution visual recognition; object-model database; ping-pong ball; Computer vision; Degradation; Image databases; Image recognition; Image resolution; Layout; Machine vision; Performance analysis; Surface texture; System performance;
Conference_Titel :
Pattern Recognition, 1990. Proceedings., 10th International Conference on
Conference_Location :
Atlantic City, NJ
Print_ISBN :
0-8186-2062-5
DOI :
10.1109/ICPR.1990.118055