A New Method for Fast Computation of Moments Based on 8-neighbor Chain CodeApplied to 2-D Objects Recognition

Guangrong Ji; G.Y. Wang; Z. Houkes; Bing Zheng; Yan-ping Han

doi:10.1109/ICIPS.1997.669116

A New Method for Fast Computation of Moments Based on 8-neighbor Chain CodeApplied to 2-D Objects Recognition

Guangrong Ji, G.Y. Wang, Z. Houkes, Bing Zheng, Yan-ping Han

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

37 Downloads (Pure)

Abstract

2D moment invariants have been successfully applied in pattern recognition tasks. The main difficulty of using moment invariants is the computational burden. To improve the algorithm of moments computation through an iterative method, an approach for fast computation of moments based on the 8-neighbor chain code is proposed in this paper. Then artificial neural networks are applied for 2D shape recognition with moment invariants. Compared with the method of polygonal approximation, this approach shows higher accuracy in shape representation and faster recognition speed in experiments

Original language	Undefined
Title of host publication	Proceedings of the IEEE ICIPS'97, vol.2
Place of Publication	Beijing, China
Publisher	IEEE
Pages	974-978
Number of pages	5
ISBN (Print)	9780780342538
DOIs	https://doi.org/10.1109/ICIPS.1997.669116
Publication status	Published - 10 Oct 1997
Event	IEEE International Conference on Intelligent Processing Systems, ICIPS '97 - Beijing, China Duration: 28 Oct 1997 → 31 Oct 1997

Publication series

Name
Publisher	IEEE Press
Volume	2

Conference

Conference	IEEE International Conference on Intelligent Processing Systems, ICIPS '97
Period	28/10/97 → 31/10/97
Other	28-31 Oct. 1997

Keywords

IR-16570
METIS-113455

Access to Document

10.1109/ICIPS.1997.669116

Ji97new
open

Cite this

@inproceedings{2f7a31ab3e0840f6a3655aef3d016572,

title = "A New Method for Fast Computation of Moments Based on 8-neighbor Chain CodeApplied to 2-D Objects Recognition",

abstract = "2D moment invariants have been successfully applied in pattern recognition tasks. The main difficulty of using moment invariants is the computational burden. To improve the algorithm of moments computation through an iterative method, an approach for fast computation of moments based on the 8-neighbor chain code is proposed in this paper. Then artificial neural networks are applied for 2D shape recognition with moment invariants. Compared with the method of polygonal approximation, this approach shows higher accuracy in shape representation and faster recognition speed in experiments",

keywords = "IR-16570, METIS-113455",

author = "Guangrong Ji and G.Y. Wang and Z. Houkes and Bing Zheng and Yan-ping Han",

year = "1997",

month = oct,

day = "10",

doi = "10.1109/ICIPS.1997.669116",

language = "Undefined",

isbn = "9780780342538",

publisher = "IEEE",

pages = "974--978",

booktitle = "Proceedings of the IEEE ICIPS'97, vol.2",

address = "United States",

note = "null ; Conference date: 28-10-1997 Through 31-10-1997",

}

A New Method for Fast Computation of Moments Based on 8-neighbor Chain CodeApplied to 2-D Objects Recognition. / Ji, Guangrong; Wang, G.Y.; Houkes, Z.; Zheng, Bing; Han, Yan-ping.

Proceedings of the IEEE ICIPS'97, vol.2. Beijing, China : IEEE, 1997. p. 974-978.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - A New Method for Fast Computation of Moments Based on 8-neighbor Chain CodeApplied to 2-D Objects Recognition

AU - Ji, Guangrong

AU - Wang, G.Y.

AU - Houkes, Z.

AU - Zheng, Bing

AU - Han, Yan-ping

PY - 1997/10/10

Y1 - 1997/10/10

N2 - 2D moment invariants have been successfully applied in pattern recognition tasks. The main difficulty of using moment invariants is the computational burden. To improve the algorithm of moments computation through an iterative method, an approach for fast computation of moments based on the 8-neighbor chain code is proposed in this paper. Then artificial neural networks are applied for 2D shape recognition with moment invariants. Compared with the method of polygonal approximation, this approach shows higher accuracy in shape representation and faster recognition speed in experiments

AB - 2D moment invariants have been successfully applied in pattern recognition tasks. The main difficulty of using moment invariants is the computational burden. To improve the algorithm of moments computation through an iterative method, an approach for fast computation of moments based on the 8-neighbor chain code is proposed in this paper. Then artificial neural networks are applied for 2D shape recognition with moment invariants. Compared with the method of polygonal approximation, this approach shows higher accuracy in shape representation and faster recognition speed in experiments

KW - IR-16570

KW - METIS-113455

U2 - 10.1109/ICIPS.1997.669116

DO - 10.1109/ICIPS.1997.669116

M3 - Conference contribution

SN - 9780780342538

SP - 974

EP - 978

BT - Proceedings of the IEEE ICIPS'97, vol.2

PB - IEEE

CY - Beijing, China

Y2 - 28 October 1997 through 31 October 1997

ER -