TY - CHAP T1 - An Experimental Study of Color-Based Segmentation Algorithms Based on the Mean-Shift Concept T2 - Computer Vision – ECCV 2010Computer Vision – ECCV 2010 Y1 - 2010 A1 - Bitsakos,K. A1 - Fermüller, Cornelia A1 - Aloimonos, J. ED - Daniilidis,Kostas ED - Maragos,Petros ED - Paragios,Nikos AB - We point out a difference between the original mean-shift formulation of Fukunaga and Hostetler and the common variant in the computer vision community, namely whether the pairwise comparison is performed with the original or with the filtered image of the previous iteration. This leads to a new hybrid algorithm, called Color Mean Shift, that roughly speaking, treats color as Fukunaga’s algorithm and spatial coordinates as Comaniciu’s algorithm. We perform experiments to evaluate how different kernel functions and color spaces affect the final filtering and segmentation results, and the computational speed, using the Berkeley and Weizmann segmentation databases. We conclude that the new method gives better results than existing mean shift ones on four standard comparison measures ( improvement on RAND and BDE measures respectively for color images), with slightly higher running times ( ). Overall, the new method produces segmentations comparable in quality to the ones obtained with current state of the art segmentation algorithms. JA - Computer Vision – ECCV 2010Computer Vision – ECCV 2010 T3 - Lecture Notes in Computer Science PB - Springer Berlin / Heidelberg VL - 6312 SN - 978-3-642-15551-2 UR - http://dx.doi.org/10.1007/978-3-642-15552-9_37 ER -