A practical pattern recognition system for translation, scale and rotation invariance

Author

Kim, Whoi-Yul ; Yuan, Po

Author_Institution

Erik Jonsson Sch. of Eng. & Comput. Sci., Texas Univ., Richardson, TX, USA

fYear

1994

fDate

21-23 Jun 1994

Firstpage

391

Lastpage

396

Abstract

We present a practical pattern recognition system that is invariant with respect to translation, scale and rotation of objects. The system is also insensitive to large variations of the threshold used. As feature vectors, Zernike moments are used and we compare them with Hu´s seven moment invariants. For a practical machine vision system, three key issues are discussed: pattern normalization, fast computation of Zernike moments, and classification using k-NN rule. As testing results, the system recognizes a set of 62 alphanumeric machine-printed characters with different sizes, at arbitrary orientations, and with different thresholds where the size of the characters varies from 10×10 to 512×512 pixels

Keywords

computer vision; pattern recognition; Zernike moments; feature vectors; image classification; k-NN rule; machine vision; moment invariants; pattern normalization; pattern recognition system; rotation invariance; scale; translation; Machine vision; Pattern classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition, 1994. Proceedings CVPR '94., 1994 IEEE Computer Society Conference on

Conference_Location

Seattle, WA

ISSN

1063-6919

Print_ISBN

0-8186-5825-8

Type

conf

DOI

10.1109/CVPR.1994.323856

Filename

323856