Abstract. End-stopped cells in cortical area V1, which combine outputs of complex cells tuned to different orientations, serve to detect line and edge crossings (junctions) and po...
This paper presents an efficient and homogeneous paradigm for automatic acquisition and recognition of nonparametric shapes. Acquisition time varies from linear to cubic in the nu...
Abstract. Most of the processing in vision today uses spatially invariant operations. This gives efficient and compact computing structures, with the conventional convenient separa...
Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...
Composition of temporal and spatial properties of real world objects in a unified data framework results into Moving Object Databases (MOD). MODs are able to process, manage and a...