A fast object recognition system using object appearances

Author

Pack, D.J.

Author_Institution

Dept. of Electr. Eng., USAF Acad., CO, USA

Volume

4

fYear

2000

fDate

2000

Firstpage

2781

Abstract

The paper presents a novel appearance-model based fast object recognition system. The speed is achieved by avoiding much of the image processing required for feature extraction and by compactly representing object models in a subspace. Raw images of an object are transformed into an object model in an eigenvector space after a simple process that compresses the data size using a low pass spatial filter along with an interpolation method. The validity of the proposed scheme is demonstrated by a working model-airplane recognition system

Keywords

aerospace computing; data compression; eigenvalues and eigenfunctions; image coding; interpolation; low-pass filters; object recognition; appearance-model based fast object recognition; data size compression; eigenvector space; fast object recognition system; feature extraction; image processing; interpolation method; low pass spatial filter; object appearances; object model; object models; raw images; subspace; working model-airplane recognition system; Airplanes; Cameras; Covariance matrix; Data mining; Feature extraction; Image processing; Matrix decomposition; Object recognition; Presses; Sensor phenomena and characterization;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 2000 IEEE International Conference on

Conference_Location

Nashville, TN

ISSN

1062-922X

Print_ISBN

0-7803-6583-6

Type

conf

DOI

10.1109/ICSMC.2000.884418

Filename

884418