Intro to Computer Vision
Lecture 10
Greg Shakhnarovich
May 4, 2010
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Guidelines and tips
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Community
Ask the community
Ask the community for help and clear up your study doubts
University Rankings
Discover the best universities in your country according to Docsity users
Free resources
Our save-the-student-ebooks!
Download our free guides on studying techniques, anxiety management strategies, and thesis advice from Docsity tutors
Binary Images-Introduction to Computer Vision-Lecture 10-Computer Science, Lecture notes of Computer Vision
Binary Images, Skin Detection, Chroma-Key Detection, Silhouette, Binary Image Morphology, Dilation, Dilation With Structuring Element, Erosion, Erosion With SE, Opening, Closing, Boundary Extraction By Erosion, Boundary by Dilation, Connected Components, Shape Matching, Shape Representation, Shape Contexts, Shape Contexts, Shape Matching and Transformation Model, Greg Shakhnarovich, Lecture Slides, Introduction to Computer Vision, Computer Science, Toyota Technological Institute at Chicago, Unit
Typology: Lecture notes
2011/2012
1 / 86
This page cannot be seen from the preview
Don't miss anything!
Related documents
Partial preview of the text
Download Binary Images-Introduction to Computer Vision-Lecture 10-Computer Science and more Lecture notes Computer Vision in PDF only on Docsity!
Intro to Computer Vision
Lecture 10
Greg Shakhnarovich
May 4, 2010
Review
Example: skin detection
Jones & Rehg 1999: model of skin color distribution from 13,
images (≈ 1 billion labeled pixels)
Example: skin detection
Given a probability models p(r, g, b | skin) and p(r, g, b) we can
classify a pixel as skin or non-skin, using Bayes rule:
p(skin | r, g, b =
p(r, g, b | skin)p(skin)
p(r, g, b)
By thresholding the value of
p(skin | r, g, b) we get a binary image
Jones & Rehg 1999
Chroma-key detection
from http://mathsci.ucd.ie/met/msc/fezzik/
Example: silhouette
Common problem: foreground-background segmentation
find objects (foreground) on top of otherwise (almost) static
background
Figure: B. Tamersoy/K. Grauman
Binary image morphology
Morphology: theory (and a set of tools) for mathematical analysis
and manipulation of 2D geometrical structures (shapes)
Operations on binary images based on neighborhoods, represented
by the structuring element
Most common SE (with center denoted by circle):
square plus disk (approx.)
Dilation: intuition
Figure: R. A. Peters, http://www.archive.org/details/Lectures on Image Processing
Dilation with structuring element
Computing D = Dilate(I): place SE at each pixel (x, y) in I
If any pixel of I covered by SE is 1, set D(x, y) = 1.
Dilation with structuring element
Computing D = Dilate(I): place SE at each pixel (x, y) in I
If any pixel of I covered by SE is 1, set D(x, y) = 1.
Dilation with structuring element
Computing D = Dilate(I): place SE at each pixel (x, y) in I
If any pixel of I covered by SE is 1, set D(x, y) = 1.
Dilation with structuring element
Computing D = Dilate(I): place SE at each pixel (x, y) in I
If any pixel of I covered by SE is 1, set D(x, y) = 1.
Dilation with structuring element
Computing D = Dilate(I): place SE at each pixel (x, y) in I
If any pixel of I covered by SE is 1, set D(x, y) = 1.
Dilation with structuring element
Computing D = Dilate(I): place SE at each pixel (x, y) in I
If any pixel of I covered by SE is 1, set D(x, y) = 1.