lecture16 - EECS 442 Computer vision Detectors part I Edge...

Info iconThis preview shows pages 1–16. Sign up to view the full content.

View Full Document Right Arrow Icon
EECS 442 – Computer vision Detectors part I Reading: [FP] Chapters: 8,9 Some slides of this lectures are courtesy of prof F. Li, prof S. Lazebnik, and various other lecturers • Edge feature detectors • Corner feature detectors
Background image of page 1

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

View Full DocumentRight Arrow Icon
Goal: Identify interesting regions from the images (edges, corners, blobs…) Descriptors Matching / Indexing / Recognition e.g. SIFT
Background image of page 2
• Convolution: ] l n , k m [ g ] l , k [ f ] n , m )[ g f ( l , k = • Smoothing • Differentiation Linear filtering
Background image of page 3

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

View Full DocumentRight Arrow Icon
• Weight contributions of neighboring pixels by nearness 0.003 0.013 0.022 0.013 0.003 0.013 0.059 0.097 0.059 0.013 0.022 0.097 0.159 0.097 0.022 0.013 0.059 0.097 0.059 0.013 0.003 0.013 0.022 0.013 0.003 5 x 5, σ = 1 Slide credit: Christopher Rasmussen Smoothing with a Gaussian
Background image of page 4
Smoothing with a Gaussian
Background image of page 5

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

View Full DocumentRight Arrow Icon
Differentiation and convolution f x fx n + 1 , y ( ) n , y ( ) Δ x Original Image 2D Kernel -1 0 1 -1 0 1 -1 0 1 2D Kernel -2 -1 0 1 2 -2 -1 0 1 2 -2 -1 0 1 2 -2 -1 0 1 2 -2 -1 0 1 2 Rudimentary edge detector!
Background image of page 6
Edge detection
Background image of page 7

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

View Full DocumentRight Arrow Icon
What causes an edge? • Depth discontinuity • Surface orientation discontinuity • Reflectance discontinuity (i.e., change in surface material properties) • Illumination discontinuity (e.g., shadow) Identifies sudden changes in an image
Background image of page 8
Edge Detection – Good detection : minimize the probability of false positives (detecting spurious edges caused by noise), false negatives (missing real edges) – Good localization : • edges must be detected as close as possible to the true edges. – Single response constraint : • minimize the number of local maxima around the true edge (i.e. detector must return single point for each true edge point) • Criteria for optimal edge detection (Canny 86):
Background image of page 9

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

View Full DocumentRight Arrow Icon
Edge Detection • Examples: True edge Poor localization Too many responses Poor robustness to noise
Background image of page 10
Designing an edge detector • Edge: a location with high gradient (thus, use derivatives!) • Need two derivatives, in x and y direction. •N e e d smoothing to reduce noise prior to taking derivative
Background image of page 11

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

View Full DocumentRight Arrow Icon
f g f * g ) ( g f dx d Source: S. Seitz
Background image of page 12
Edge by Derivative of Gaussian • We can use derivative of Gaussian filters •Gaussian filter is needed for smoothing the image Why? •Differentiation can be modeled by a convolution • Convolution is associative: (G * I) = (D * G) * I D *
Background image of page 13

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

View Full DocumentRight Arrow Icon
Edge by Derivative of Gaussian
Background image of page 14
– Most widely used edge detector in computer vision.
Background image of page 15

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

View Full DocumentRight Arrow Icon
Image of page 16
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 59

lecture16 - EECS 442 Computer vision Detectors part I Edge...

This preview shows document pages 1 - 16. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online