An Alternative Curvature Measure for Topographic Feature Detection
The notion of topographic features like ridges, trenches, hills, etc. is formed by visualising the 2D image function as a surface in 3D space. Hence, properties of such a surface can be used to detect features from images. One such property, the curvature of the image surface, can be used to detect features characterised by a sharp bend in the surface. Curvature based feature detection requires an efficient technique to estimate/calculate the surface curvature. In this paper, we present an alternative measure for curvature and provide an analysis of the same to determine its scope. Feature detection algorithms using this measure are formulated and two applications are chosen to demonstrate their performance. The results show good potential of the proposed measure in terms of efficiency and scope.
KeywordsFeature Detection Image Surface Curvature Measure Medial Point Crest Line
Unable to display preview. Download preview PDF.
- 4.Monga, O., Armande, N., Montesinos, P.: Thin nets and crest lines: Applications to satellite data and medical images. In: Proc. IEEE Conference of Image Processing, vol. 2, pp. 468–471 (1995)Google Scholar
- 5.Fan, T., Medioni, G., Nevatia, R.: Description of surfaces from range data using curvature properties. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 86–91 (1986)Google Scholar
- 7.Flynn, P.J., Jain, A.K.: On reliable curvature estimation. In: Proc. of the International Conference on Computer Vision and Pattern Recognition, pp. 110–116 (1989)Google Scholar
- 8.Chandra, S., Sivaswamy, J.: An analysis of curvature based ridge and valley detection. In: Proc. of International conference on Acoustics speech and signal processing (ICASSP) (2006)Google Scholar
- 10.Chandra, S.: Analysis of retinal angiogram images. M.S. Thesis, Centre for Visual Information Technology, IIIT Hyderabad, India (2005)Google Scholar