Computer Vision: Recognition with Global Representations II (Di, 25.11.2014)

Anmeldung erforderlich

RWTH

Für RWTH-Angehörige und aus dem RWTH-Netz verfügbar

Anmelden
  • Einbetten

Kapitel:

00:00:23
Course Outline
00:01:26
Recap: Appearance-Based Recognition
00:02:37
Recap: Recognition Using Histograms
00:03:30
Recap: Comparison Measures
00:06:19
Recap: Recognition Using Histograms
00:09:19
Generalization of the Idea
00:11:22
General Filter Response Histograms
00:12:07
Multidimensional Representations
00:13:02
Multidimensional Histograms
00:13:32
Multidimensional Representations
00:16:58
Special Case: Multiscale Representations
00:20:33
Generalization: Filter Banks
00:22:30
Example Application of a Filter Bank
00:23:08
Extension: Colored Derivatives
00:26:56
Summary: Multidimensional Representations
00:29:28
Application: Brand Identification in Video
00:31:25
You're Now Ready for First Applications...
00:34:00
Topics of This Lecture
00:35:14
Representations for Recognition
00:37:16
Example: The Space of All Face Images
00:38:52
The Space of All Face Images
00:40:36
Subspace Methods
00:42:45
Subspace Methods
00:44:24
Topics of This Lecture
00:44:39
Principal Component Analysis
00:46:53
Principal Component Analysis
00:50:19
Remember: Fitting a Gaussian
00:51:06
Interpretation of PCA
00:52:09
Interpretation of PCA
00:53:08
Interpretation of PCA
00:54:04
Properties of PCA
00:59:02
Projection and Reconstruction
01:01:27
Example: Object Representation
01:01:59
Principal Component Analysis
01:04:28
Object Detection by Distance TO Eigenspace
01:05:56
Eigenfaces: Key Idea
01:07:45
Eigenfaces Example
01:07:49
Eigenfaces: Key Idea
01:07:56
Eigenfaces Example
01:08:07
Eigenfaces Example
01:08:51
Eigenfaces Example
01:08:59
Eigenfaces Example
01:09:22
Eigenface Example 2 (Better Alignment)
01:17:48
Eigenfaces Example
01:19:48
Recognition with Eigenspaces
01:21:10
Object Identification by Distance IN Eigenspace
01:22:45
Parametric Eigenspace
01:24:10
Applications: Recognition, Pose Estimation
01:27:00
Applications: Visual Inspection
01:29:49
Important Footnote
01:31:10
Singular Value Decomposition (SVD)
01:31:46
References and Further Reading