Image segmentation by using the localized sub- space iteration algorithm

An image segmentation algorithm called “segmentation based on the localized subspace iterations” (SLSI) is proposed in this paper. The basic idea is to combine the strategies in Ncut algorithm by Shi and Malik [Normalized cuts and image segmentation, IEEE Trans. Pattern Anal. Mach. Intel. 22 (2000), 888-905] and the LSI by E, Li and Lu [Localized basis of eigen-subspaces and operator compression, submitted to Proc. Nat. Acad. Sci., 2007]. The LSI is applied to solve an eigenvalue problem associated with the affinity matrix of an image, which makes the overall algorithm linearly scaled. The choices of the partition number, the supports and weight functions in SLSI are discussed. Numerical experiments for real images show the applicability of the algorithm.