Image datablase construction and search algorithm for smart pixel optoelectronic systems

摘要

The extraordinary increase of digital image contents requires the development of methods to classify or quickly search video sequences in movie databases. In this paper, we suggest a novel agorithm based on Eigen value de-composition to construct and search video databases, and that can be implemented using smart pixel optoelectronic systems. By successive iterations the images are progresively classified in sets and sugbsets in a tree-type configuration. To evaluate this method, a movie containing 2,262 frames has been analyzed, and a sucessful classification of these images in function of their contents was obtained. The realization of this algotihm on a semart pixel system called OCULAR-II~1 is also discussed, and a demonstration of the database search algotihm on the OCULAR-II system is described.