Segmentation using eigenvectors分割使用特征向量.pptVIP

Segmentation using eigenvectors Papers: “Normalized Cuts and Image Segmentation”. Jianbo Shi and Jitendra Malik, IEEE, 2000 “Segmentation using eigenvectors: a unifying view”. Yair Weiss, ICCV 1999. Presenter: Carlos Vallespi cvalles@ Image Segmentation Image segmentation How do you pick the right segmentation? “Correct” segmentation There may not be a single correct answer. Partitioning is inherently hierarchical. One approach we will use in this presentation: “Use the low-level coherence of brightness, color, texture or motion attributes to come up with partitions” Outline Introduction Graph terminology and representation. “Min cuts” and “Normalized cuts”. Other segmentation methods using eigenvectors. Conclusions. Outline Introduction Graph terminology and representation. “Min cuts” and “Normalized cuts”. Other segmentation methods using eigenvectors. Conclusions. Graph-based Image Segmentation Graph-based Image Segmentation Graph-based Image Segmentation Graph-based Image Segmentation Outline Introduction Graph terminology and representation. “Min cuts” and “Normalized cuts”. Other segmentation methods using eigenvectors. Conclusions. Graph-based Image Segmentation Graph terminology Similarity matrix: Affinity matrix Graph terminology Degree of node: Graph terminology Volume of set: Graph terminology Representation Partition matrix X: Pair-wise similarity matrix W: Degree matrix D: Laplacian matrix L: Pixel similarity functions Pixel similarity functions Definitions Methods that use the spectrum of the affinity matrix to cluster are known as spectral clustering. Normalized cuts, Average cuts, Average association make use of the eigenvectors of the affinity matrix. Why these methods work? Spectral Clustering Eigenvectors and blocks Block matrices have block eigenvectors: Near-block matrices have near-block eigenvectors: Spectral Space Outline Introduction Graph terminology and representation. “Min cuts” and “Normalized cuts”. Other seg