Object Indexing Using an Iconic Sparse Distributed Memory

A general-purpose object indexingtechnique is described that combines the virtues of principal component analysis with the favorable matching properties of high-dimensional spaces to achieve high precision recognition. An object is represented by a set of high-dimensionaliconic feature vectors comprised of the responses of derivative of Gaussian filters at a range of orientations and scales. Since these filters can be shown to form the eigenvectors of arbitrary images containing both natural and man-made structures, they are well-suited for indexing in disparate domains. The indexing algorithm uses an active vision system in conjunction with a modified form of Kanerva’s sparse distributed memory which facilitates interpolation between views and provides a convenient platform for learning the association between an object’s appearance andits identity. The robustness of the indexing method was experimentally confirmed by subjecting the method to a range of viewing conditions and...

• Type: Conference
• Year: 1995
• Where: ICCV
• Authors: Rajesh P. N. Rao, Dana H. Ballard
• Keywords: Computer Vision, Favorable Matching Properties, General-purpose Object Indexingtechnique, ICCV 1995, Principal Component Analysis