1 / 42

Segmentation

Segmentation. Grouping and Segmentation. Grouping and Segmentation appear to be one of the early processes in human vision They are a way of *organizing* image content into “semantically related” groups

Lucy
Télécharger la présentation

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. Segmentation Copyright G.D. Hager

  2. Grouping and Segmentation • Grouping and Segmentation appear to be one of the early processes in human vision • They are a way of *organizing* image content into “semantically related” groups • In some applications, segmentation is the crucial step (e.g. some types of aerial image interpretation). Copyright G.D. Hager

  3. Grouping and Segmentation • Grouping is the process of associating similar image features together Copyright G.D. Hager

  4. Grouping and Segmentation • Grouping is the process of associating similar image features together • The Gestalt School: • Proximity:tokens that are nearby tend to be grouped. • Similarity:similar tokens tend to be grouped together. • Common fate:tokens that have coherent motion tend to be grouped together. • Common region:tokens that lie inside the same closed region tend to be grouped together. • Parallelism:parallel curves or tokens tend to be grouped together. • Closure:tokens or curves that tend to lead to closed curves tend to be grouped together. • Symmetry:curves that lead to symmetric groups are grouped together. • Continuity:tokens that lead to “continuous ” (as in “joining up nicely ”, rather than in the formal sense): curves tend to be grouped. • Familiar Conguration: tokens that, when grouped, lead to a familiar object,tend to be grouped together Copyright G.D. Hager

  5. Copyright G.D. Hager

  6. Copyright G.D. Hager

  7. Copyright G.D. Hager

  8. Grouping and Segmentation • Segmentation is the process of dividing an image into regions of “related content” Courtesy Uni Bonn Copyright G.D. Hager

  9. Grouping and Segmentation • Segmentation is the process of dividing an image into regions of “related content” Courtesy Uni Bonn Copyright G.D. Hager

  10. Grouping and Segmentation • Both are an ill defined problem --- related or similar is often a high-level, cognitive notion • The literature on segmentation and grouping is large and generally inconclusive --- we’ll discuss a couple of algorithms and an example. Copyright G.D. Hager

  11. Simple Thresholding • Choose an image criterion c • Compute a binary image by b(i,j) = 1 if c(I(i,j)) > t; 0 otherwise • Perform “cleanup operations” (image morphology) • Perform grouping • Compute connected components and/or statistics thereof Copyright G.D. Hager

  12. An Example: Motion Detecting motion: Copyright G.D. Hager

  13. Thresholded Motion Detecting motion: 50 Candidate areas for motion Copyright G.D. Hager

  14. A Closer Look Copyright G.D. Hager

  15. Color: A Second Example Already seen in the tracking lecture (quick recap) Copyright G.D. Hager

  16. Homogeneous Color Region: Photometry Copyright G.D. Hager

  17. Homogeneous Region: Photometry PCA-fitted ellipsoid Sample Copyright G.D. Hager

  18. Binary Image Processing After thresholding an image, we want to know usually the following about the regions found ... How many objects are in the image? Where are the distinct “object” components? Copyright G.D. Hager

  19. Connected Component Labeling Goal: Label contiguous areas of a segmented image with unique labels 0 1 2 One uses a 4-neighbor or 8-neighbor connectivity Copyright G.D. Hager

  20. Limitations of Thresholding • A uniform threshold may not apply across the image • It measures the uniformity of regions (in some sense), but doesn’t examine the inter-relationship between regions. • Local “disturbances” can break up nominally consistent regions Copyright G.D. Hager

  21. More General Segmentation • Region Growing: • Tile the image • Start a region with a seed tile • Merge similar neighboring tiles in the region body • When threshold exceeded, start a new region • Region Splitting • Start with one large region • Recursively • Choose the region with highest dissimilarity • If sufficiently similar, stop, otherwise split • repeat until no more splitting occurs Bottom-up approach Top-down approach Copyright G.D. Hager

  22. Another Example: Image Segmentation • The goal: to choose regions of the image that have similar “statistics.” • Possible statistics: • mean • Variance • Histograms Copyright G.D. Hager

  23. An Image Histogram Copyright G.D. Hager

  24. How does one form a histogram? • Let us consider a gray scale image for simplicity (image values ranging from 0-255) • Select the number of bins n (max 256 bins) • Width of each bin is 256/n. If n = 8, width = 32 • Set counter for each bin to zero. • Now for each pixel, depending on its gray scale value, increment the counter of the bin where the gray scale value of the pixel falls. • The final counter values of the bins is the histogram of the image for the specified number of bins. 0-32 33-64 65-96 Copyright G.D. Hager

  25. Comparing Histograms Copyright G.D. Hager

  26. Which is More Similar? .906 .266 Copyright G.D. Hager

  27. Results of a Merge Segmentation Copyright G.D. Hager

  28. More Examples Copyright G.D. Hager

  29. Algorithm Choose a fixed number of clusters and initial cluster centers Allocate points to clusters that they are closest too Recompute the cluster centers Go back to step 2, and repeat until convergence K-Means Copyright G.D. Hager

  30. Image Clusters on intensity Clusters on color K-means clustering using intensity alone and color alone Copyright G.D. Hager

  31. An Example: BlobWorld(Carson, Belongie, Greenspan, Malik) The problem: query images (e.g. from the WEB) using image information The solution: segment images into roughly uniform regions and search based on feature vectors The features: color texture location (i.e. spatial compactness) Copyright G.D. Hager

  32. Example Segmentations Copyright G.D. Hager

  33. Querying User selects a weighting of color vs. texture giving a diagonal weight matrix S Given a blob with feature vector vi, compared to another vector vj using Mahalanobis distance: di,j = (vi – vj)tS (vi – vj) Compound queries using min and max for and and or Copyright G.D. Hager

  34. Copyright G.D. Hager

  35. Copyright G.D. Hager

  36. Copyright G.D. Hager

  37. Copyright G.D. Hager

  38. More Complex Segmentation Methods • Snakes • Level Sets • Graph Cuts • Generalized PCA Copyright G.D. Hager

  39. Snakes Copyright G.D. Hager Images taken from http://www.cs.bris.ac.uk/home/xie/content.htm

  40. Level Sets Copyright G.D. Hager Images taken from http://www.cgl.uwaterloo.ca/~mmwasile/cs870/

  41. Graph Cuts Copyright G.D. Hager Images taken from efficient graph-based segmentation paper

  42. GPCA (Rene Vidal) Human GPCA Copyright G.D. Hager

More Related