25 September 1998 Systolic array for fast computation of moment invariants
Author Affiliations +
Proceedings Volume 3545, International Symposium on Multispectral Image Processing (ISMIP'98); (1998) https://doi.org/10.1117/12.323608
Event: International Symposium on Multispectral Image Processing, 1998, Wuhan, China
Abstract
Moment invariants, by virtue of invariance properties under translation, scaling and rotation, have played an important role in pattern recognition and computer vision. In the present paper, extending the systolic array for computing moments, a global systolic structure for fast computation of moment invariants has been proposed. This structure fully exploits parallelism of the network architecture and reduces computational time complexity from O(n2) in the case of direct computation to O(n) (n denotes image size). The systolic structure nearly consists of adders with area complexity O(n) and are highly regular and structurally very simple, resulting in simple hardware implementation. The method is suitable for both binary images and gray level images and is also suitable for image sequence moments.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jianguo Liu, Francis H. Y. Chan, H. F. Li, F. K. Lam, "Systolic array for fast computation of moment invariants", Proc. SPIE 3545, International Symposium on Multispectral Image Processing (ISMIP'98), (25 September 1998); doi: 10.1117/12.323608; https://doi.org/10.1117/12.323608
PROCEEDINGS
4 PAGES


SHARE
RELATED CONTENT

Digital image reconstruction using Zernike moments
Proceedings of SPIE (February 06 2004)
Principal curve detection in complicated graph images
Proceedings of SPIE (September 20 2001)
GPGPU real-time texture analysis framework
Proceedings of SPIE (January 25 2011)
Knowledge-Based Image Segmentation
Proceedings of SPIE (March 27 1987)

Back to Top