DocumentCode :
454897
Title :
An Analysis of Curvature Based Ridge and Valley Detection
Author :
Chandra, Siva ; Sivaswamy, Jayanthi
Author_Institution :
Int. Inst. of Inf. Technol., Hyderabad
Volume :
2
fYear :
2006
fDate :
14-19 May 2006
Abstract :
A 2D function, representing a digital image, is a surface in 3D space. Curvature of such a surface can be exploited to detect ridge and valley like features from images. In this paper, we present an analysis of such curvature based ridge and valley detection techniques and come up with a description for the different classes of ridge and valley profiles which can be detected by them. Such an analysis helps in understanding the scope and limitations of the curvature based techniques. As curvature is a measure of ´bend´ in the cross-section profile along a particular direction of the image intensities, the analysis is presented using ID functions which represent cross-section profiles of ridges and valleys. The classes of profiles which can be detected by a curvature based technique are described in terms of the properties of the second-derivative of the ID profile function
Keywords :
geophysical signal processing; object detection; remote sensing; ID profile function; cross-section profiles; curvature based ridge detection; image intensities; valley detection; Biomedical imaging; Computer vision; Digital images; Geometry; Image analysis; Information technology; Particle measurements; Satellites; Space technology; Visualization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location :
Toulouse
ISSN :
1520-6149
Print_ISBN :
1-4244-0469-X
Type :
conf
DOI :
10.1109/ICASSP.2006.1660448
Filename :
1660448
Link To Document :
بازگشت