Curvature scale space for robust image corner detection

Mokhtarian, Farzin; Suomela, Riku

doi:10.1109/icpr.1998.712083

Cited by 21 publications

(19 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We obtain a smooth curve and handle noisy edge shapes at the same time by using a Gaussian smoothing of the curve, similarly to Curvature Scale Space (CSS) [8]. Smoothed joints have higher curvature than their neighborhood and can always be detected as a curvature critical point.…”

Section: Invariant Feature Extractionmentioning

confidence: 99%

Spatial Topology Graphs for Feature-Minimal Correspondence

Tauber

Li²,

Drew³

2007

Fourth Canadian Conference on Computer and Robot Vision (CRV '07)

View full text Add to dashboard Cite

show abstract

Section: Invariant Feature Extractionmentioning

confidence: 99%

Spatial Topology Graphs for Feature-Minimal Correspondence

Tauber

Li²,

Drew³

2007

Fourth Canadian Conference on Computer and Robot Vision (CRV '07)

View full text Add to dashboard Cite

show abstract

“…Other corner detectors have been proposed in [27][28][29][30]. Mokhtarian [31] used the curvature-scalespace (CSS) [32], [33] technique to search the corner points. The CSS technique is adopted by MPEG-7.…”

Section: Introductionmentioning

confidence: 99%

Image Corner Detection Using Hough Transform

Kang

Choung

Park

2005

Pattern Recognition and Image Analysis

View full text Add to dashboard Cite

Abstract. This paper describes a new corner detection algorithm based on the Hough Transform. The basic idea is to find the straight lines in the images and then search for their intersections, which are the corner points of the objects in the images. The Hough Transform is used for detecting the straight lines and the inverse Hough Transform is used for locating the intersection points among the straight lines, and hence determine the corner points. The algorithm was tested on various test images, and the results are compared with well-known algorithms.

show abstract

“…The most common boundary based shape descriptors are chain codes and Fourier descriptors in multiple resolution. During recent years curvature scale space (CSS) shape representation is used [9] for image corner detection.Dengsheng Zhang et al [4] made a comparative study of fourier descriptors for shape representation using different fourier invarients. The study shows that among shape signatures complex coordinates, centroid distance is the best shape signature for shape retrieval.…”

Section: Literature Surveymentioning

confidence: 99%