Join DELOS - MUSCLE Summer School on Multimedia digital libraries, Machine learning and cross-modal technologies for access and retrieval

Feature extraction & content description I

author: Nicu Sebe, University of Amsterdam

Categories

Top: Computer Science: Image Analysis
Top: Computer Science: Computer Vision

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Feature Extraction and Content Description
1:22	Prelude
1:37	Prelude
2:30	Index
2:32	The trouble with images - the modeling gap
3:01	the semantic gap
3:41	the semantic gap
4:21	the sensory gap
5:18	conclusions
6:16	conclusions
7:01	Index
7:07	Picture
7:44	Hall of fame
8:24	electromagnetic spectrum
8:50	Spectral power distribution
9:35	the triplet light-objects-observer
10:01	the triplet light-objects-observer: reconsidered
10:23	Light sources and illuminants
10:43	Influence of light sources and illuminants
11:02	Influence of light sources and illuminants
11:26	Index
11:30	This makes the image
12:05	Colorimetry: CIE XYZ-system
12:41	Colorimetry: xy-system
12:57	Colorimetry: Illuminants in the xy-plane
13:01	Colorimetry: colour gamuts in the xy-plane
13:12	Colour camera: The RGB-colour space
13:38	Colour camera: The rgb-colour space
14:12	Colour camera: H,S,I definitions
15:41	Opponent colors
16:18	Lab colour space
16:45	Colour circle: warm and cool colours
17:06	Colour harmony
17:54	Colour harmony
19:20	Index
19:32	Picture
20:01	general model
21:02	detailed model
21:58	body reflectance in RGB - space
22:30	body reflectance in RGB – space: matte surfaces
23:18	body reflectance in RGB - space
23:37	body reflectance in RGB - space
24:16	reflectance under white light
24:40	reflectance under white light reconsidered
25:07	RGB - space
25:44	RGB - space
26:03	rgb – photometric invariance: proof
26:35	matte objects
27:45	matte objects
28:10	c1c2c3 space
28:50	c1c2c3 space
29:39	Hue is viewpoint invariant
29:47	Hue is viewpoint invariant
30:09	Shiny objects
30:33	Shiny objects: l1l2l3l - space
31:13	Shiny objects: l1l2l3l - space
31:47	Colour constancy
32:07	Colour constancy
32:40	Colour constancy using higlights
33:16	Colour by correlation
33:43	Colour by correlation
34:18	Colour ratios: diagonal model
34:46	Colour ratios: model
35:55	Colour ratios
36:30	Colour ratios
36:43	Taxonomy
42:37	Illustrations
43:15	Experiments on retrieval by example
43:47	Grass detection: example
44:46	shape
44:51	Shape
45:09	Index
45:28	taxonomy of image structures
46:13	taxonomy of image structures: reflectance and geometry
47:19	overview of photometric invariances (see above)
48:04	colour edge detection
48:10	colour edge detection
48:13	colour edge detection
49:13	detection of highlights in HSI-space
49:45	detection of shadow invariant corners: the Njet
50:28	The detection of shadow invariant corners: the Hessian
50:59	classification in HSI-space: highlights
51:19	classification in ??? space: shadow T-junctions
51:30	classification in HSB – space: highlights
52:10	classification in HSB – space: geometry edges
52:34	classification in RGB – space: corners
52:48	classification of color edges
53:21	classification of color edges
54:02	classification of color edges
54:23	classification of color edges
54:36	colour edge classification real time demo
55:13	colour edge classification real time demo
55:36	colour edge classification real time demo
55:53	Index - Object shape
56:12	Object shape
56:24	multi-scale, example: SQUID
56:54	normalized moments
57:03	example: QBIC system
57:18	conclusion: feature selection
57:59	Index - Shape similarity
58:02	Shape through transformation
58:19	Shape through transformation
58:42	Shape through transformation
59:11	Real time demo
59:45	Real time demo
60:27	Texture: 2-D Gabor filters

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.