A machine vision identification technique from range imagesAn orientation-independent identification technique from three-dimensional surface maps or range images is developed. Given the range image of an object, it is decomposed into orientation-independent patches using the sign of Gaussian curvature. A relational graph is then set up such that a node represents a patch and an edge represents the adjacency of two patches. The identification of the object is achieved by matching its graph representation to a number of model graphs. The matching is performed by employing the best-first search strategy. Examples of real range images show the merit of the technique.
Document ID
19890024404
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Kehtarnavaz, N. (Texas A&M Univ. College Station, TX, United States)
Mohan, S. (Texas A & M University College Station, United States)