Title :
Recognizing mice, vegetables and hand printed characters based on implicit polynomials, invariants and Bayesian methods
Author :
Subrahmonia, Jayashree ; Keren, Daniel ; Cooper, David B.
Author_Institution :
Lab. for Eng. Man/Machine Syst., Brown Univ., Providence, RI, USA
Abstract :
The authors present a robust low-computational-cost system for recognizing freeform objects in 3-D range data or in 2-D curve data in the image plane. Objects are represented by implicit polynomials, i.e., 3-D algebraic surfaces or 2-D algebraic curves of degrees greater than two, and are recognized by computing and matching vectors of their algebraic invariants, which are functions of their coefficients that are invariant to translations, rotations, and general linear transformations. Implicit polynomials of fourth degree can represent complicated asymmetric free-form shapes. A design of Bayesian recognizers for these models and their invariants that results in low-computational-cost recognizers robust to noise, partial occlusion, and other perturbations of the data sets is considered. This work extends the work of D. Keren et al. (1992) by developing and using new invariants for 3-D surface polynomials and applying the Bayesian recognizer to operating on invariants
Keywords :
Bayes methods; character recognition; image recognition; object recognition; polynomials; 2-D algebraic curves; 2-D curve data; 3-D algebraic surfaces; 3-D range data; 3-D surface polynomials; Bayesian methods; complicated asymmetric free-form shapes; data sets; freeform objects recognition; general linear transformations; hand printed characters; image plane; implicit polynomials; invariants; matching; mice; partial occlusion; rotations; translations; vegetables; Bayesian methods; Character recognition; Computational efficiency; Data engineering; Databases; Image recognition; Laboratories; Mice; Polynomials; Systems engineering and theory;
Conference_Titel :
Computer Vision, 1993. Proceedings., Fourth International Conference on
Conference_Location :
Berlin
Print_ISBN :
0-8186-3870-2
DOI :
10.1109/ICCV.1993.378198