Direct Curvature Scale Space: Theory and Corner Detection

Author

Zhong, Baojiang ; Liao, Wenhe

Author_Institution

Dept. of Math., Nanjing Univ. of Aeronaut. & Astronaut.

Volume

29

Issue

3

fYear

2007

fDate

3/1/2007 12:00:00 AM

Firstpage

508

Lastpage

512

Abstract

The curvature scale space (CSS) technique is considered to be a modern tool in image processing and computer vision. direct curvature scale space (DCSS) is defined as the CSS that results from convolving the curvature of a planar curve with a Gaussian kernel directly. In this paper we present a theoretical analysis of DCSS in detecting corners on planar curves. The scale space behavior of isolated single and double corner models is investigated and a number of model properties are specified which enable us to transform a DCSS image into a tree organization and, so that corners can be detected in a multiscale sense. To overcome the sensitivity of DCSS to noise, a hybrid strategy to apply CSS and DCSS is suggested

Keywords

Gaussian processes; computer vision; object detection; Gaussian kernel; computer vision; direct curvature scale space; image processing; planar curves; Analysis of variance; Cascading style sheets; Computer vision; Convolution; Detectors; Image processing; Kernel; Shape; Signal analysis; Smoothing methods; Gaussian smoothing; Scale space; corner detection.; curvature; curve convolution; Algorithms; Artificial Intelligence; Cluster Analysis; Image Enhancement; Image Interpretation, Computer-Assisted; Normal Distribution; Pattern Recognition, Automated;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/TPAMI.2007.50

Filename

4069267