1 / 17

Edge Detection

Edge Detection. Our goal is to extract a “line drawing” representation from an image Useful for recognition: edges contain shape information invariance. Derivatives. Edges are locations with high image gradient or derivative Estimate derivative using finite difference Problem?. Smoothing.

walker-mitchell
Download Presentation

Edge Detection

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. Edge Detection

  2. Our goal is to extract a “line drawing” representation from an image • Useful for recognition: edges contain shape information • invariance

  3. Derivatives • Edges are locations with high image gradient or derivative • Estimate derivative using finite difference • Problem?

  4. Smoothing • Reduce image noise by smoothing with a Gaussian

  5. Edge orientation • Would like gradients in all directions • Approximate: • Compute smoothed derivatives in x,y directions • Edge strength • Edge normal

  6. Canny Edge Detection • Compute edge strength and orientation at all pixels • “Non-max suppression” • Reduce thick edge strength responses around true edges • Link and threshold using “hysteresis” • Simple method of “contour completion”

  7. Non-maximum suppression: • Select the single maximum point across the width of an edge. Slides by D. Lowe

  8. Non-maximum suppression At q, the value must be larger than values interpolated at p or r.

  9. Examples: Non-Maximum Suppression courtesy of G. Loy Non-maxima suppressed Original image Gradient magnitude Slide credit: Christopher Rasmussen

  10. fine scale high threshold

  11. coarse scale, high threshold

  12. coarse scale low threshold

  13. Linking to the next edge point Assume the marked point is an edge point. Take the normal to the gradient at that point and use this to predict continuation points (either r or s).

  14. Edge Hysteresis • Hysteresis:A lag or momentum factor • Idea: Maintain two thresholds khigh and klow • Use khigh to find strong edges to start edge chain • Use klow to find weak edges which continue edge chain • Typical ratio of thresholds is roughly khigh/klow=2

  15. gap is gone Example: Canny Edge Detection Strong + connected weak edges Original image Strong edges only Weak edges courtesy of G. Loy

  16. Problem? • Texture • Canny edge detection responds all over textured regions

More Related