lecture18 - EECS 442 Computer vision Segmentation &...

Info iconThis preview shows pages 1–22. Sign up to view the full content.

View Full Document Right Arrow Icon
EECS 442 – Computer vision Segmentation & Clustering Reading: Chapters 14 [FP] • Segmentation in human vision • K-mean clustering •Mean-sh ift • Graph-cut Some slides of this lectures are courtesy of prof F. Li, prof S. Lazebnik, and various other lecturers
Background image of page 1

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

View Full DocumentRight Arrow Icon
Background image of page 2
Segmentation • Compact representation for image data in terms of a set of components • Components share “common” visual properties • Properties can be defined at different level of abstractions
Background image of page 3

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

View Full DocumentRight Arrow Icon
General ideas •To ken s – whatever we need to group (pixels, points, surface elements, etc., etc.) • Bottom up segmentation – tokens belong together because they are locally coherent • Top down segmentation – tokens belong together because they lie on the same object > These two are not mutually exclusive
Background image of page 4
What is Segmentation? • Clustering image elements that “belong together” – Partitioning • Divide into regions/sequences with coherent internal properties – Grouping • Identify sets of coherent tokens in image Slide credit: Christopher Rasmussen
Background image of page 5

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

View Full DocumentRight Arrow Icon
Why do these tokens belong together? What is Segmentation?
Background image of page 6
Basic ideas of grouping in human vision • Figure-ground discrimination • Gestalt properties
Background image of page 7

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

View Full DocumentRight Arrow Icon
– Grouping can be seen in terms of allocating some elements to a figure, some to ground – Can be based on local bottom-up cues or high level recognition Figure-ground discrimination
Background image of page 8
Figure-ground discrimination
Background image of page 9

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

View Full DocumentRight Arrow Icon
–A s e r i e s o f factors affect whether elements should be grouped together Gestalt properties
Background image of page 10
Gestalt properties
Background image of page 11

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

View Full DocumentRight Arrow Icon
Gestalt properties
Background image of page 12
Gestalt properties Grouping by occlusions
Background image of page 13

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

View Full DocumentRight Arrow Icon
Gestalt properties Grouping by invisible completions
Background image of page 14
Emergence
Background image of page 15

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

View Full DocumentRight Arrow Icon
Segmentation in computer vision J. Malik, S. Belongie, T. Leung and J. Shi. " Contour and Texture Analysis for Image Segmentation ". IJCV 43(1),7-27,2001.
Background image of page 16
Object Recognition as Machine Translation, Duygulu, Barnard, de Freitas, Forsyth, ECCV02 Segmentation in computer vision
Background image of page 17

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

View Full DocumentRight Arrow Icon
Segmentation as clustering Cluster together tokens that share similar visual characteristics •K-mean •Mean-sh ift • Graph-cut
Background image of page 18
Feature Space • Every token is identified by a set of salient visual characteristics. For example: – Position – Color –T e x t u r e – Motion vector – Size, orientation (if token is larger than a pixel) Slide credit: Christopher Rasmussen
Background image of page 19

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

View Full DocumentRight Arrow Icon
Source: K. Grauman Feature Space
Background image of page 20
Feature space: each token is represented by a point r b g
Background image of page 21

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

View Full DocumentRight Arrow Icon
Image of page 22
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 10/26/2010 for the course EECS 442 taught by Professor Savarese during the Fall '09 term at University of Michigan.

Page1 / 73

lecture18 - EECS 442 Computer vision Segmentation &...

This preview shows document pages 1 - 22. Sign up to view the full document.

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