Segmentation attempted via contour/boundary detection
CSE 803 Fall 2008 Stockman 4
Clustering versus region-growing
CSE 803 Fall 2008 Stockman 5
Clustering versus region-growing
CSE 803 Fall 2008 Stockman 6
K-means clustering as before: vectors can contain color+texture
CSE 803 Fall 2008 Stockman 7
K-means
CSE 803 Fall 2008 Stockman 8
Histograms can show modes
CSE 803 Fall 2008 Stockman 9
Otsu’s method assumes K=2. It searches for the threshold t that optimizes the intra class variance.
CSE 803 Fall 2008 Stockman 10
Ohlander bifurcated the histogram recursively
CSE 803 Fall 2008 Stockman 11
Recursive histogram-controlled segmentation
CSE 803 Fall 2008 Stockman 12
URL’s of other work Segmentation lecture http://robots.stanford.edu/cs223b/index .html Tutorial on graph cut method and assessment of segmentation http://www.cis.upenn.edu/~jshi/GraphT utorial/
CSE 803 Fall 2008 Stockman 13
Segmentation via region- growing (aggregation)
Pixels, or patches, at the lowest
level are combined when similar in a hierarchical fashion
CSE 803 Fall 2008 Stockman 14
Decision: combine neighbors?
Neighboring pixel or region
CSE 803 Fall 2008 Stockman 15
Aggregation decision
CSE 803 Fall 2008 Stockman 16
Representation of regions
CSE 803 Fall 2008 Stockman 17
Chain codes for boundaries
CSE 803 Fall 2008 Stockman 18
Quad trees divide into quadrants
M=mixed; E=empty; F=full
CSE 803 Fall 2008 Stockman 19
Can segment 3D images also Oct trees subdivide into 8 octants Same coding: M, E, F used Software available for doing 3D image processing and differential equations using octree representation. Can achieve large compression factor.
CSE 803 Fall 2008 Stockman 20
More URLs of other work Mean shift description http://cmp.felk.cvut.cz/cmp/courses/ZS 1/slidy/meanShiftSeg.pdf