1 / 32

CAP 5415 Computer Vision Fall 2004

CAP 5415 Computer Vision Fall 2004. Dr. Alper Yilmaz Univ. of Central Florida www.cs.ucf.edu/courses/cap5415/fall2004 Office: CSB 250. Recap (Edge Detection). Marr-Hildreth and Canny edge detectors Gaussian smoothing Compute derivatives In x and y directions Find gradient magnitude

amma
Download Presentation

CAP 5415 Computer Vision Fall 2004

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. CAP 5415 Computer VisionFall 2004 Dr. Alper Yilmaz Univ. of Central Florida www.cs.ucf.edu/courses/cap5415/fall2004 Office: CSB 250 Alper Yilmaz, Fall 2004 UCF

  2. Recap (Edge Detection) • Marr-Hildreth and Canny edge detectors • Gaussian smoothing • Compute derivatives • In x and y directions • Find gradient magnitude • Threshold gradient magnitude • Difference between Marr-Hildreth and Canny • Marr-Hildreth use 2nd order derivative • Marr-Hildreth thresholds slope of zero-crossings Alper Yilmaz, Fall 2004 UCF

  3. Marr-Hildreth Edge Detector Image 2g(x) Find zero-crossings compute slope Threshold Alper Yilmaz, Fall 2004 UCF

  4. Canny Edge Detector gx(x,y) Gradient magnitude Image Non-maximum suppression Hysteresis thresholding gy(x,y) Gradient direction Alper Yilmaz, Fall 2004 UCF

  5. Region Segmentation Marr Hildreth Edge Detector Canny Edge Detector Alper Yilmaz, Fall 2004 UCF

  6. Applications of Segmentation • Object recognition • MPEG-4 video compression Alper Yilmaz, Fall 2004 UCF

  7. Object Recognition Using Region Properties • Training • For all training samples of each model object • Segment the image • Compute region properties (features) • Recognition • Given an image of unknown object, • Segment the image • Compute its feature vector • Compare with the training set Alper Yilmaz, Fall 2004 UCF

  8. MPEG4 CompressionObject Based Compression • Advantages of OBC • High compression ratio • Allows insertion deletion of objects • How does it work? • Find objects (Object Segmentation) • Code objects and their locations • Build mosaics of globally static objects • Render scene at receiver Alper Yilmaz, Fall 2004 UCF

  9. Clustering Alper Yilmaz, Fall 2004 UCF

  10. Segmentation-Clustering R4 R1 R2 R6 R3 R5 Alper Yilmaz, Fall 2004 UCF

  11. Region Segmentation Alper Yilmaz, Fall 2004 UCF

  12. Layer Representation Alper Yilmaz, Fall 2004 UCF

  13. Segmentation • Find set of regions R1, R2, ….,Rn such that • All pixels in region i satisfy some similarity constraint Alper Yilmaz, Fall 2004 UCF

  14. Similarity Constraints • All pixels in any sub-image musts have the same gray levels. • All pixels in any sub-image must not differ more than some threshold • All pixels in any sub-image may not differ more than some threshold from the mean of the gray of the region • The standard deviation of gray levels in any sub-image must be small. Alper Yilmaz, Fall 2004 UCF

  15. Simple Segmentation Alper Yilmaz, Fall 2004 UCF

  16. Image Histogram • Histogram graphs the number of pixels with a particular gray level as a function of the image of gray levels. number of pixels gray level Alper Yilmaz, Fall 2004 UCF

  17. Segmentation Using HistogramSimple Case Alper Yilmaz, Fall 2004 UCF

  18. Segmentation Using HistogramSimple Case Alper Yilmaz, Fall 2004 UCF

  19. Realistic Histograms Not realistic Real (noise) Alper Yilmaz, Fall 2004 UCF

  20. Realistic Histograms • Smooth out noise • Convolve hist. by averaging or 1D Gaussian filter peak peak valley peak valley valley Alper Yilmaz, Fall 2004 UCF

  21. Segmentation Using HistogramReal image histograms • Compute the histogram of a given image. • Smooth the histogram by averaging peaks and valleys in the histogram. • Detect good peaks by applying thresholds at the valleys. • Segment the image into several binary images using thresholds at the valleys. • Apply connected component algorithm to each binary image find connected regions. Alper Yilmaz, Fall 2004 UCF

  22. Good PeaksPeakiness Test Alper Yilmaz, Fall 2004 UCF

  23. Segmentation Using Histograms • Select the valleys as thresholds • Apply threshold to histogram • Label the pixels within the range of a threshold with same label, i.e., a, b, c … or 1, 2, 3 … Alper Yilmaz, Fall 2004 UCF

  24. Connected Components • Disjoint segments with same labels need to be split may be added to segment c Alper Yilmaz, Fall 2004 UCF

  25. Recursive Connected Component Algorithm Alper Yilmaz, Fall 2004 UCF

  26. Sequential Connected Component Algorithm Alper Yilmaz, Fall 2004 UCF

  27. Sequential Connected Component Algorithm d=c Equivalence class Alper Yilmaz, Fall 2004 UCF

  28. ExampleDetecting Finger Tips (marked white) Alper Yilmaz, Fall 2004 UCF

  29. ExampleSegmenting a bottle image 93 peaks Alper Yilmaz, Fall 2004 UCF

  30. ExampleSegmenting a bottle image Smoothed histogram (averaging using mask Of size 5) 54 peaks (once) After peakiness 18 Smoothed histogram 21 peaks (twice) After peakiness 7 Smoothed histogram 11 peaks (three times) After peakiness 4 Alper Yilmaz, Fall 2004 UCF

  31. ExampleSegmenting a bottle image (0,40) (40, 116) (116,243) (243,255) Alper Yilmaz, Fall 2004 UCF

  32. Suggested Reading • Chapter 3, Mubarak Shah, “Fundamentals of Computer Vision” Alper Yilmaz, Fall 2004 UCF

More Related