1 / 24

Announcements

Learn about edge detection, gradient direction, Sobel operator, Laplacian of Gaussian, Canny edge detector, and more. Understand how to extract salient features from images efficiently.

pmerryman
Download Presentation

Announcements

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. Announcements • Project 0 due tomorrow night

  2. Edge Detection • Today’s readings • Cipolla and Gee (handout) • supplemental: Forsyth, chapter 9 • For Friday • Watt, 10.3-10.4 (handout) • Intelligent Scissors • http://www.cs.washington.edu/education/courses/490cv/02wi/readings/book-7-revised-a-indx.pdf From Sandlot Science

  3. Edge detection • Convert a 2D image into a set of curves • Extracts salient features of the scene • More compact than pixels

  4. Origin of Edges • Edges are caused by a variety of factors. surface normal discontinuity depth discontinuity surface color discontinuity illumination discontinuity

  5. Edge detection • How can you tell that a pixel is on an edge? snoop demo

  6. The gradient direction is given by: • how does this relate to the direction of the edge? • The edge strength is given by the gradient magnitude Image gradient • The gradient of an image: • The gradient points in the direction of most rapid change in intensity

  7. The discrete gradient • How can we differentiate a digital image F(x,y)? • Option 1: reconstruct a continuous image, then take gradient • Option 2: take discrete derivative (finite difference) • How would you implement this as a cross-correlation? filter demo

  8. The Sobel operator • Better approximations of the derivatives exist • The Sobel operators below are very commonly used • The standard defn. of the Sobel operator omits the 1/8 term • doesn’t make a difference for edge detection • the 1/8 term is needed to get the right gradient value, however

  9. Effects of noise • Consider a single row or column of the image • Plotting intensity as a function of position gives a signal • Where is the edge?

  10. Solution: smooth first • Where is the edge? Look for peaks in

  11. Derivative theorem of convolution • This saves us one operation:

  12. Laplacian of Gaussian • Look for zero-crossings of Laplacian of Gaussian operator

  13. 2D edge detection filters • is the Laplacian operator: Laplacian of Gaussian Gaussian derivative of Gaussian

  14. The Canny edge detector • original image (Lena)

  15. The Canny edge detector • norm of the gradient

  16. The Canny edge detector • thresholding

  17. The Canny edge detector • thinning • (non-maximum suppression, edge following)

  18. The Canny edge detector • thinning • (non-maximum suppression, edge following)

  19. Effect of Gaussian kernel width original Canny with Canny with • The choice of depends on desired behavior • large detects large scale edges • small detects fine features

  20. Edge detection by subtraction original

  21. Edge detection by subtraction smoothed (5x5 Gaussian)

  22. Edge detection by subtraction Why does this work? smoothed – original (scaled by 4, offset +128)

  23. Gaussian - subtraction filter Gaussian Impulse Laplacian of Gaussian

  24. Summary • Things to take away from this lecture • What is an edge and where does it come from • Edge detection by differentiation • Image gradients • continuous and discrete • filters (e.g., Sobel operator) • Effects of noise on gradients • Derivative theorem of convolution • Derivative of Gaussian (DoG) operator • Laplacian operator • Laplacian of Gaussian (LoG) • Canny edge detector (basic idea) • Effects of varying sigma parameter • Approximating an LoG by subtraction

More Related