1 / 54

Normalized Cuts and Image Segmentation

Normalized Cuts and Image Segmentation. Jianbo Shi and Jitendra Malik, Presented by: Alireza Tavakkoli. Image Segmentation. Image segmentation. How do you pick the right segmentation?. Bottom up segmentation: - Tokens belong together because they are locally coherent.

sherrij
Download Presentation

Normalized Cuts and Image Segmentation

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Normalized Cuts and Image Segmentation Jianbo Shi and Jitendra Malik, Presented by: Alireza Tavakkoli

  2. Image Segmentation

  3. Image segmentation • How do you pick the right segmentation? • Bottom up segmentation: • - Tokens belong together because • they are locally coherent. • Top down segmentation: • - Tokens grouped because • they lie on the same object.

  4. “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”

  5. Outline • Introduction • Graph terminology and representation. • “Min cuts” and “Normalized cuts”. • Other segmentation methods using eigenvectors. • Conclusions.

  6. Outline • Introduction • Graph terminology and representation. • “Min cuts” and “Normalized cuts”. • Other segmentation methods using eigenvectors. • Conclusions.

  7. Graph-based Image Segmentation Image (I) Intensity Color Edges Texture Graph Affinities (W) Slide from Timothee Cour (http://www.seas.upenn.edu/~timothee)

  8. Graph-based Image Segmentation Image (I) Intensity Color Edges Texture Graph Affinities (W) Slide from Timothee Cour (http://www.seas.upenn.edu/~timothee)

  9. Graph-based Image Segmentation Image (I) Eigenvector X(W) Intensity Color Edges Texture Graph Affinities (W) Slide from Timothee Cour (http://www.seas.upenn.edu/~timothee)

  10. Graph-based Image Segmentation Image (I) Eigenvector X(W) Discretization Intensity Color Edges Texture Graph Affinities (W) Slide from Timothee Cour (http://www.seas.upenn.edu/~timothee)

  11. Outline • Introduction • Graph terminology and representation. • “Min cuts” and “Normalized cuts”. • Other segmentation methods using eigenvectors. • Conclusions.

  12. Graph-based Image Segmentation G = {V,E} V: graph nodes E: edges connection nodes Pixels Pixel similarity Slides from Jianbo Shi

  13. Graph terminology • Similarity matrix: Slides from Jianbo Shi

  14. Affinity matrix N pixels Similarity of image pixels to selected pixel Brighter means more similar M pixels Warning the size of W is quadratic with the number of parameters! Reshape N*M pixels N*M pixels

  15. Graph terminology • Degree of node: … … Slides from Jianbo Shi

  16. Graph terminology • Volume of set: Slides from Jianbo Shi

  17. Graph terminology • Cuts in a graph: Slides from Jianbo Shi

  18. segments pixels Representation Partition matrix X: Pair-wise similarity matrix W: Degree matrix D: Laplacian matrix L:

  19. Pixel similarity functions Intensity Distance Texture

  20. Pixel similarity functions Intensity here c(x) is a vector of filter outputs. A natural thing to do is to square the outputs of a range of different filters at different scales and orientations, smooth the result, and rack these into a vector. Distance Texture

  21. 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?

  22. Spectral Clustering Data Similarities * Slides from Dan Klein, Sep Kamvar, Chris Manning, Natural Language Group Stanford University

  23. Eigenvectors and blocks • Block matrices have block eigenvectors: • Near-block matrices have near-block eigenvectors: 3= 0 1= 2 2= 2 4= 0 eigensolver 3= -0.02 1= 2.02 2= 2.02 4= -0.02 eigensolver * Slides from Dan Klein, Sep Kamvar, Chris Manning, Natural Language Group Stanford University

  24. Spectral Space • Can put items into blocks by eigenvectors: • Clusters clear regardless of row ordering: e1 e2 e1 e2 e1 e2 e1 e2 * Slides from Dan Klein, Sep Kamvar, Chris Manning, Natural Language Group Stanford University

  25. Outline • Introduction • Graph terminology and representation. • “Min cuts” and “Normalized cuts”. • Other segmentation methods using eigenvectors. • Conclusions.

  26. How do we extract a good cluster? • Simplest idea: we want a vector x giving the association between each element and a cluster • We want elements within this cluster to, on the whole, have strong affinity with one another • We could maximize • But need the constraint • This is an eigenvalue problem - choose the eigenvector of W with largest eigenvalue.

  27. Cuts with lesser weight than the ideal cut Ideal Cut Minimum cut • Criterion for partition: A Problem! Weight of cut is directly proportional to the number of edges in the cut. B First proposed by Wu and Leahy

  28. Normalized Cut Normalized cut or balanced cut: Finds better cut

  29. Normalized Cut • Volume of set (or association): A B

  30. Normalized Cut • Volume of set (or association): • Define normalized cut: “a fraction of the total edge connections to all the nodes in the graph”: A B A B • Define normalized association: “how tightly on average nodes within the cluster are connected to each other” A B

  31. Observations(I) • Maximizing Nassoc is the same as minimizing Ncut, since they are related: • How to minimize Ncut? • Transform Ncut equation to a matricial form. • After simplifying: NP-Hard! y’s values are quantized Subject to: Rayleigh quotient

  32. min Observations(II) • Instead, relax into the continuous domain by solving generalized eigenvalue system: • Which gives: • Note that so, the first eigenvector is y0=1 with eigenvalue 0. • The second smallest eigenvector is the real valued solution to this problem!!

  33. Algorithm • Define a similarity function between 2 nodes. i.e.: • Compute affinity matrix (W) and degree matrix (D). • Solve • Use the eigenvector with the second smallest eigenvalue to bipartition the graph. • Decide if re-partition current partitions. Note: since precision requirements are low, W is very sparse and only few eigenvectors are required, the eigenvectors can be extracted very fast using Lanczos algorithm.

  34. Discretization • Sometimes there is not a clear threshold to binarize since eigenvectors take on continuous values. • How to choose the splitting point? • Pick a constant value (0, or 0.5). • Pick the median value as splitting point. • Look for the splitting point that has the minimum Ncut value: • Choose n possible splitting points. • Compute Ncut value. • Pick minimum.

  35. Use k-eigenvectors • Recursive 2-way Ncut is slow. • We can use more eigenvectors to re-partition the graph, however: • Not all eigenvectors are useful for partition (degree of smoothness). • Procedure: compute k-means with a high k. Then follow one of these procedures: • Merge segments that minimize k-way Ncut criterion. • Use the k segments and find the partitions there using exhaustive search. • Compute Q (next slides). e1 e2 e1 e2

  36. Example Eigenvectors Segments

  37. Experiments • Define similarity: • for point sets. • for brightness images. • for HSV images. • in case of texture.

  38. Experiments (I) • Point set segmentation: (a) Pointset generated by Poisson process. (b) Segmentation results.

  39. Experiments (II) • Synthetic images:

  40. Experiments (III) • Weather radar:

  41. Experiments (IV) • Motion segmentation

  42. Outline • Introduction • Graph terminology and representation. • “Min cuts” and “Normalized cuts”. • Other segmentation methods using eigenvectors. • Conclusions.

  43. Other methods • Average association • Use the eigenvector of W associated to the biggest eigenvalue for partitioning. • Tries to maximize: • Has a bias to find tight clusters. Useful for Gaussian distributions. A B

  44. Other methods • Average cut • Tries to minimize: • Very similar to normalized cuts. • We cannot ensure that partitions will have a a tight within-group similarity since this equation does not have the nice properties of the equation of normalized cuts.

  45. Other methods

  46. Other methods Normalized cut Average cut 20 points are randomly distributed from 0.0 to 0.5 12 points are randomly distributed from 0.65 to 1.0 Average association

  47. Other methods Normalized cut Average cut 20 points are randomly distributed from 0.0 to 0.5 12 points are randomly distributed from 0.65 to 1.0 Average association

  48. Other methods Normalized cut Average cut 20 points are randomly distributed from 0.0 to 0.5 12 points are randomly distributed from 0.65 to 1.0 Average association

  49. Outline • Introduction • Graph terminology and representation. • “Min cuts” and “Normalized cuts”. • Other segmentation methods using eigenvectors. • Conclusions.

  50. Conclusions • Good news: • Simple and powerful methods to segment images. • Flexible and easy to apply to other clustering problems. • Bad news: • High memory requirements (use sparse matrices). • Very dependant on the scale factor for a specific problem.

More Related