Object recognition via hierarchical syntactic models

Author

Gidas, B. ; Zelic, A.

Author_Institution

Div. of Appl. Math., Brown Univ., Providence, RI, USA

Volume

1

fYear

1997

fDate

2-4 Jul 1997

Firstpage

315

Abstract

We propose a multiple-object recognition framework based on: (a) context-free-grammars type hierarchical syntactic models for representing objects in a database, and (b) nonparametric statistics (rank tests of Kolmogorov-Smirnov statistics) for designing local descriptors of grey-level image data. The procedure has been successfully tested on a database of 2-D simulated tools in an environment highly degraded by noise, blur, clutter, and occlusion

Keywords

context-free grammars; digital simulation; dynamic programming; image representation; nonparametric statistics; object recognition; visual databases; 2D simulated tools; Kolmogorov-Smirnov statistics; blur; clutter; context free grammars; data models; database; dynamic programming; grey-level image data; hierarchical syntactic models; local descriptors; multiple-object recognition; noise; nonparametric statistics; occlusion; Data models; Deformable models; Feature extraction; Hidden Markov models; Image databases; Object recognition; Solid modeling; Speech recognition; Statistical analysis; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Signal Processing Proceedings, 1997. DSP 97., 1997 13th International Conference on

Conference_Location

Santorini

Print_ISBN

0-7803-4137-6

Type

conf

DOI

10.1109/ICDSP.1997.628082

Filename

628082