{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

CSE527-l5 - Lecture Layout Perceptual and Sensory Augmented...

Info iconThis preview shows pages 1–12. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Perceptual and Sensory Augmented Computing Lecture Layout Image features Edges Junctions & Corners Blobs Ridges Image descriptors SIFT features Goals for a low-level image representation Compact Reduce the number of processed image locations 000000011111100000111111111000 = 000000 01 1111 10 000 01 1111111 10 00 = 7x0 5x1 5x0 7x1 3x0 Generic Sufficient No need to look back into the image 2
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
2 Boundaries: 1-D structures in 2-D from O(N^2) to O(N) Corners/Junctions: 0-D structures: O(1) (`Boundaries of boundaries’) Boundaries 3 Attneave, 1954 A biref anlaogy wtih txet Waht mttares is waht hpapens on wrod baounrdies Mocpera iwht htsi (compare with this) Massive evidence of our visual system employing boundary detection 4
Background image of page 2
3 Symmetries 5 Perceptual and Sensory Augmented Computing Lecture Layout Image features Edges Junctions & Corners Blobs Ridges Image descriptors SIFT features
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
4 Edges in images Edges are not only object boundaries… … and object boundaries do not always cause edges 7 surface normal discontinuity shape depth discontinuity boundaries surface color discontinuity texture illumination discontinuity shadows Object Boundaries vs. Edges Background Texture Shadows
Background image of page 4
5 Perceptual and Sensory Augmented Computing Lecture Layout Image features Edges 1D edge detection 2D edge detection Laplacian-of-Gaussian Canny edge detection Recent research Junctions & Corners Blobs Ridges Image descriptors SIFT features Edges: discontinuities in the image intensity function Estimate derivative, find its peaks and we are done Finding edges image
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
6 Finding edges in real images Consider images corrupted with Gaussian noise image Why does this happen? Consider Fourier transform Magnitude, |F| Add noise Multiply FTs
Background image of page 6
7 Last lecture: smoothing to remove noise 13 First convolve signal with Gaussian filter d/dx Convolve Last lecture: smoothing to remove noise 14 Large scales: increased robustness to noise But poor localization accuracy Convolve d/dx
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
8 Convolution with Gaussian: windowing of FT Frequency-domain explanation 15 Multiply Multiply Smaller kernel width: higher frequencies Scaling property of Fourier transform: 16 Multiply Multiply
Background image of page 8
9 Find edges at minima/maxima of derivative Condition for extremum: derivative equal to zero Edge localization 17 Convolve d/dx d/dx Differentiation, smoothing: linear operators (filters) Cascade of filters can be replaced with a single filter Differentiation property of convolution: Convolve with and detect zero-crossings All-in-one filter 18
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
10 19 1D edge detection: summary 1st derivative 2nd derivative Multi-scale 1D edge detection As σ increases, the smoothing increases and only the central edge survives.
Background image of page 10
11 Perceptual and Sensory Augmented Computing Lecture Layout Image features Edges 1D edge detection 2D edge detection Laplacian-of-Gaussian Canny edge detection Recent research
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 12
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}