Generalized Principal Component Analysis (GPCA) thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Generalized Principal Component Analysis (GPCA)

Published on Feb 25, 200719384 Views

Data segmentation is usually though of as a chicken-and-egg problem. In order to estimate a mixture of models one needs to first segment the data, and in order to segment the data one needs to know th

Related categories

Chapter list

Generalized Principal Component Analysis: Theory and Applications in Computer Vision00:03
Outline03:14
Part I: Generalized Principal Component Analysis04:20
Principal Component Analysis (PCA)04:32
Extensions of PCA05:59
Applications of GPCA in vision and control10:15
Generalized Principal Component Analysis15:19
Our approach to segmentation: GPCA21:57
Introductory example: algebraic clustering in 1D24:10
Introductory example: algebraic clustering in 1D28:09
Introductory example: algebraic clustering in 2D34:09
Intensity-based image segmentation36:29
Intensity-based image segmentation37:36
Intensity-based image segmentation38:05
Intensity-based image segmentation39:12
Texture-based image segmentation39:14
Texture-based image segmentation41:41
Representing one subspace41:56
Representing n subspaces44:07
Fitting polynomials to data points48:17
Finding a basis for each subspace (1)52:54
Finding a basis for each subspace (2)56:57