A New Technique to Classify Symmetrical Images using Regular Moments

P. Raveendran; Sigeru Omatu; Poh Sin Chew

A New Technique to Classify Symmetrical Images using Regular Moments

P. Raveendran, Sigeru Omatu, Poh Sin Chew

Research output: Contribution to conference › Paper › peer-review

Abstract

It is a well known fact that symmetrical images in the x- and/or y- directions give zero values for odd regular moments. This poses some problems in classification. Here, we address this problem and propose a method to solve it. The solution involves the computation of regular moments from the centres other than the centroid of the image, the centres being selected in such a way that the invariant properties such as translation, scale, rotation, and/or reflection of the regular moments are preserved. Illustrative computer simulations verify the validity of the proposed method.

Original language	English
Pages	405-408
Number of pages	4
Publication status	Published - 1998
Externally published	Yes
Event	Joint Conference on Information Sciences 1998 - Research Triangle Park, United States of America Duration: 23 Oct 1998 → 28 Oct 1998 Conference number: 4th

Conference

Conference	Joint Conference on Information Sciences 1998
Abbreviated title	JCIS 1998
Country/Territory	United States of America
City	Research Triangle Park
Period	23/10/98 → 28/10/98

Cite this

@conference{3e60cf0622774cda8a151b0738e2cdcb,

title = "A New Technique to Classify Symmetrical Images using Regular Moments",

abstract = "It is a well known fact that symmetrical images in the x- and/or y- directions give zero values for odd regular moments. This poses some problems in classification. Here, we address this problem and propose a method to solve it. The solution involves the computation of regular moments from the centres other than the centroid of the image, the centres being selected in such a way that the invariant properties such as translation, scale, rotation, and/or reflection of the regular moments are preserved. Illustrative computer simulations verify the validity of the proposed method.",

author = "P. Raveendran and Sigeru Omatu and Chew, {Poh Sin}",

year = "1998",

language = "English",

pages = "405--408",

note = "Joint Conference on Information Sciences 1998, JCIS 1998 ; Conference date: 23-10-1998 Through 28-10-1998",

}

TY - CONF

T1 - A New Technique to Classify Symmetrical Images using Regular Moments

AU - Raveendran, P.

AU - Omatu, Sigeru

AU - Chew, Poh Sin

N1 - Conference code: 4th

PY - 1998

Y1 - 1998

N2 - It is a well known fact that symmetrical images in the x- and/or y- directions give zero values for odd regular moments. This poses some problems in classification. Here, we address this problem and propose a method to solve it. The solution involves the computation of regular moments from the centres other than the centroid of the image, the centres being selected in such a way that the invariant properties such as translation, scale, rotation, and/or reflection of the regular moments are preserved. Illustrative computer simulations verify the validity of the proposed method.

AB - It is a well known fact that symmetrical images in the x- and/or y- directions give zero values for odd regular moments. This poses some problems in classification. Here, we address this problem and propose a method to solve it. The solution involves the computation of regular moments from the centres other than the centroid of the image, the centres being selected in such a way that the invariant properties such as translation, scale, rotation, and/or reflection of the regular moments are preserved. Illustrative computer simulations verify the validity of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=1642282830&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:1642282830

SP - 405

EP - 408

T2 - Joint Conference on Information Sciences 1998

Y2 - 23 October 1998 through 28 October 1998

ER -

A New Technique to Classify Symmetrical Images using Regular Moments

Abstract

Conference

Other files and links

Cite this