Hierarchical, modular architectures for object recognition by parts
Authors:
- J.K. AggarwalJAJ.K. Aggarwal
- 1 January 1996
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (10514651) , 601-606 vol.1
Abstract
We present a methodology for object recognition by parts. The methodology is based on a hierarchical, modular structure for object recognition. Recognition is performed at different levels in the hierarchy, and the type of recognition performed differs from level to level. Each level is made up of modules, where each module is an expert on a particular part of an object, that is, each module is specifically trained to recognize one part of an object. We present a Bayesian system in which the expert modules represent the probability density functions of each part, modeled as a mixture of densities to incorporate different views (aspects) of each part. Results obtained for object recognition in second generation forward looking infrared (FLIR) images are also presented in this paper.Keywords
This publication has 7 references indexed in Scilit:
- Recognition by Functional PartsComputer Vision and Image Understanding, 1995
- Parts of visual form: computational aspectsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1995
- Model-based object recognition in dense-range images—a reviewACM Computing Surveys, 1993
- Invariant image recognition by Zernike momentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Part Segmentation for Object RecognitionNeural Computation, 1989
- Automatic Target Recognition: State of the Art SurveyIEEE Transactions on Aerospace and Electronic Systems, 1986
- Human image understanding: Recent research and a theoryComputer Vision, Graphics, and Image Processing, 1985