Notes

Slide Show

Outline

1	Edge Detection Today’s reading Cipolla & Gee on edge detection (available online)
2	Announcements
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
5	Edge detection How can you tell that a pixel is on an edge?
6	Images as functions…
7	Image gradient The gradient of an image:
8	The discrete gradient How can we differentiate a digital image F[x,y]?
9	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”)
10	The Sobel operator Better approximations of the derivatives exist The Sobel operators below are very commonly used
11	Effects of noise Consider a single row or column of the image Plotting intensity as a function of position gives a signal
12	Solution: smooth first
13	Derivative theorem of convolution This saves us one operation:
14	Laplacian of Gaussian Consider
15	2D edge detection filters
16	The Canny edge detector original image (Lena)
17	The Canny edge detector
18	The Canny edge detector
19	The Canny edge detector
20	Non-maximum suppression Check if pixel is local maximum along gradient direction requires checking interpolated pixels p and r
21	Effect of s (Gaussian kernel spread/size)
22	Edge detection by subtraction
23	Edge detection by subtraction
24	Edge detection by subtraction
25	Gaussian - image filter