Novel Statistical Approaches to the Quantitative Combination of Multiple Edge Detectors
This paper aims at describing a new framework which allows for the quantitative combination of different edge detectors based on the correspondence between the outcomes of a preselected set of operators. This is inspired from the problem that despite the enormous amount of literature on edge detection techniques, there is no single one that performs well in every possible image context. The so called Kappa Statistics are employed in a novel fashion to enable a sound performance evaluation of the edge maps emerged from different parameter specifications. The proposed method is unique in the sense that the balance between the false detections (False Positives and False Negatives) is explicitly assessed in advanced and incorporated in the estimation of the optimum threshold. Results of this technique are demonstrated and compared to individual edge detection methods.
KeywordsEdge Detection Weight Kappa Edge Image Edge Pixel True Edge
Unable to display preview. Download preview PDF.
- 6.Fleiss, J.L.: Statistical Methods For Rates and Proportions. Wiley series in probability and mathematical statistics (1981)Google Scholar
- 7.Giannarou, S., Stathaki, T.: Edge detection using quantitative combination of multiple operators. In: SiPS conference, IEEE Workshop on Signal Processing Systems (November 2005)Google Scholar
- 9.Kirkwood, B.R., Sterne, J.A.C.: Essential medical statistics. Blackwell Science, Oxford (2003)Google Scholar
- 10.Kraemer, H.C.: Evaluating Medical Test: Objective and Quantitative Guidelines. Saga Publications, Newbury Park (1992)Google Scholar
- 12.Lacroix, V.: The primary raster: a multiresolution image description. In: Proceedings. 10th International Conference on Pattern Recognition, June 1990, vol. 1, pp. 903–907 (1990)Google Scholar
- 14.Matthews, J.: An introduction to edge detection: The sobel edge detector (2002), Available at: http://www.generation5.org/content/2002/im01.asp
- 17.Rothwell, C.A., Mundy, J.L., Hoffman, W., Nguyen, V.D.: Driving vision by topology. In: Int’1 Symp. Computer Vision, November 1995, pp. 395–400. Coral Gables Fla (1995)Google Scholar
- 18.Schunck, B.G.: Edge detection with gaussian filters at multiple scales. In: Proc. IEEE Comouter Siciety Workshop on Computer Vision, pp. 208–210 (1987)Google Scholar
- 19.Sim, J., Wright, C.C.: The kappa statistic in reliability studies: Use, interpretation, and sample size requirements. Journal of the American Physical Therapy 85(3), 257–268 (2005)Google Scholar
- 20.Ulrich, M., Steger, C.: Empirical performance evaluation of object recognition methods. In: Christensen, H.I., Phillips, P.J. (eds.) Empirical Evaluation Methods in Computer Vision, pp. 62–76. IEEE Computer Society Press, Los Alamitos (2001)Google Scholar