|
Vol: 54(68) No: 1 / March 2009 Automatic Parametrisation of Image Processing Algorithms Szabolcs Sergyán Department of Software Technology, Budapest Tech, John von Neumann Faculty of Informatics, Bécsi út 96/b, H-1034 Budapest, Hungary, phone: (361) 666-5540, e-mail: sergyan.szabolcs@nik.bmf.hu, web: http://nik.bmf.hu/sergyan László Csink Department of Software Technology, Budapest Tech, John von Neumann Faculty of Informatics, Bécsi út 96/b, H-1034 Budapest, Hungary, phone: (361) 666-5581, e-mail: csink.laszlo@nik.bmf.hu, web: http://nik.bmf.hu/csink Keywords: automated parameter determination, image databases, image segmentation, edge detection Abstract The most frequently used image processing algorithms normally use parameters. The results depend on these parameters to a great degree. Normally the parameters are optimized to a set of given images, and then they use the set parameters for each new image. In many cases this can be done easily, as for a given type of images the best parameters are the same. However, when one works with a huge image database, one cannot optimize the parameters for each image. In such a case one makes a compromise, and uses parameters that fit for most images. It would be better, though, to try to find the optimal parameters for each image. In this paper we discuss two automatic parameterization algorithms, one for image segmentation and another one for edge detection. References [1] Sz. Sergyán, L. Csink, “Automatic Parametrization of Region Finding Algorithms in Gray Images”, Proceedings of 4th International Symposium on Applied Computational Intelligence and Informatics, Timisoara, Romania, May 17-18, 2007,pp. 199-202. [2] L. Csink, Sz. Sergyán, “Automatic Parametrization of Edge Detection Algorithms”, Proceedings of 5th International Symposium on Intelligent Systems and Informatics}, Subotica, Serbia, August 24-25, 2007, pp. 119-121. [3] Sz. Sergyán Sz., L. Csink, “Kísérletek a szín-alapú tartomány felismerés terén” Informatika a Felsőoktatásban 2005 Konferencia, Debrecen, 2005.~aug.~24-26. [4] E. Trucco, A. Verri, “Introductory Techniques for 3-D Conputer Vision”, Prentice-Hall, Upper Saddle River, United States of America, 1998. [5] R.C. Gonzalez, R.E. Woods, “Digital Image Processing”, Prentice-Hall, Upper Saddle River, United States of America, 2002. [6] J. Matas, “Colour-Based Object Recognition”, PhD thesis, Department of Electronic and Electrical Engineering, University of Surrey, 1996. [7] W.L.G. Koontz, P.M. Narenda, K. Fukunaga, “A Graph-theoretic Approach to Nonparametric Clustering”, IEEE Transactions on Computers, pp. 936-944, 1976. [8] J.M. Geusebroek, G.J. Burghouts, A.W.M. Smeulders, “The Amsterdam Library of Object Images”, International Journal of Computer Vision, vol. 61, no. 1, pp. 103-112, 2005. [9] W.K. Pratt, “Digital Image Processing”, Wiley, Hoboken, United States of America, 2007. |