This paper describes a fast algorithm to compute local axial moments used for the detection of objects of interest in images. The basic idea is grounded on the elimination of redundant operations while computing axial moments for two neighboring angles of orientation. The main result is that the complexity of recursive computation of axial moments becomes independent of the total number of computed moments in a given point, i.e. it is of the order O(N) where N is the data size. This result is of great importance in computer vision since many feature extraction methods are based on the computation of axial moments. The experimental results confirm the time complexity and accuracy predicted by the theoretical analysis. © 2001 IEEE.
Palenichka, R., Zaremba, M., Valenti, C. (2001). A fast recursive algorithm for the computation of axial moments. In Proceedings - 11th International Conference on Image Analysis and Processing, ICIAP 2001 (pp.95-100). IEEE Computer Society [10.1109/ICIAP.2001.956991].
A fast recursive algorithm for the computation of axial moments
VALENTI, Cesare Fabio
2001-01-01
Abstract
This paper describes a fast algorithm to compute local axial moments used for the detection of objects of interest in images. The basic idea is grounded on the elimination of redundant operations while computing axial moments for two neighboring angles of orientation. The main result is that the complexity of recursive computation of axial moments becomes independent of the total number of computed moments in a given point, i.e. it is of the order O(N) where N is the data size. This result is of great importance in computer vision since many feature extraction methods are based on the computation of axial moments. The experimental results confirm the time complexity and accuracy predicted by the theoretical analysis. © 2001 IEEE.File | Dimensione | Formato | |
---|---|---|---|
00956991.pdf
Solo gestori archvio
Dimensione
661.78 kB
Formato
Adobe PDF
|
661.78 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.