1 March 1992 Automatic building and supervised discrimination learning of appearance models of 3-D objects
Author Affiliations +
Abstract
Mechanisms for automatically building and refining appearance models (AMs) of 3-D objects are presented. AMs encode allowed ranges of values of target characteristics called attributes. Allowed values for each attribute of arbitrarily defined parts of a modeled object are determined by statistical analysis of an example set of known targets. Once models are built, the system learns which attributes are discriminating (important to making a correct identification) from mistakes made on a set of training data. In discrimination learning, a weight associated with an attribute is increased or decreased whenever a test for an attribute denies or supports an incorrect object identification, respectively. A consistently decreasing weight eventually results in the essential elimination of the associated attribute from the AM. We illustrate and evaluate this approach in the context of our work in automatic target recognition (ATR).
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Richard L. Delanoy, Jacques G. Verly, Dan E. Dudgeon, "Automatic building and supervised discrimination learning of appearance models of 3-D objects", Proc. SPIE 1708, Applications of Artificial Intelligence X: Machine Vision and Robotics, (1 March 1992); doi: 10.1117/12.58600; https://doi.org/10.1117/12.58600
PROCEEDINGS
12 PAGES


SHARE
Back to Top