Content-Based Image and Video Retrieval

Front Cover
Springer Science & Business Media, Apr 30, 2002 - Computers - 182 pages
1 Review

The amount of audiovisual information available in digital format has grown exponentially in recent years. Gigabytes of new images, audio and video clips are generated and stored everyday. Most audiovisual content can be accessed through the Internet, which is a very large, unstructured, distributed information database. Searching and retrieving multimedia information from the Web has been limited to the use of keywords.

Over the past decade, many researchers, mostly from the Image Processing and Computer Vision community, have started to investigate possible ways of retrieving visual information based solely on its contents. Instead of being manually annotated using keywords, images and video clips would be indexed by their own visual content, such as color, texture, objects' shape and movement, among others. Research in the field of content-based image and video retrieval (CBIVR) is very active. Many research groups in leading universities, research institutes, and companies are actively working in this field. Their ultimate goal is to enable users to retrieve the desired image or video clip among massive amounts of visual data in a fast, efficient, semantically meaningful, friendly, and location-independent manner. Applications of CBIVR systems include digital libraries, video-on-demand systems, geographic information systems, astronomical research, satellite observation systems, and criminal investigation systems, among many others.

Content-Based Image And Video Retrieval addresses the basic concepts and techniques for designing content-based image and video retrieval systems. It also discusses a variety of design choices for the key components of these systems. This book gives a comprehensive survey of the content-based image retrieval systems, including several content-based video retrieval systems. The survey includes both research and commercial content-based retrieval systems. Content-Based Image And Video Retrieval, includes pointers to two hundred representative bibliographic references on this field, ranging from survey papers to descriptions of recent work in the area, entire books and more than seventy websites. Finally, the book presents a detailed case study of designing MUSE–a content-based image retrieval system developed at Florida Atlantic University in Boca Raton, Florida.

Content-Based Image And Video Retrieval is designed to meet the needs of a professional audience composed of researchers, and practitioners in industry and graduate-level students in Computer Science and Engineering.

 

What people are saying - Write a review

We haven't found any reviews in the usual places.

Contents

INTRODUCTION
1
FUNDAMENTALS OF CONTENTBASED IMAGE AND VIDEO RETRIEVAL
7
2 A Typical CBIVR System Architecture
9
3 The Users Perspective
11
4 Summary
12
DESIGNING A CONTENTBASED IMAGE RETRIEVAL SYSTEM
15
11 Feature Classification and Selection
16
12 ColorBased Features
18
324 Photobook
72
325 Picasso
74
326 PicHunter
76
327 PicSOM
77
328 PicToSeek
78
329 QBIC Query By Image Content
79
330 Quicklook2
81
331 Shoebox
83

122 Representation of Color Properties
21
123 Other Parameters
23
124 Additional Remarks
24
13 TextureBased Features
25
14 ShapeBased Features
26
2 Similarity Measurements
27
3 Dimension Reduction and Highdimensional Indexing
28
5 The Semantic Gap
29
7 Relevance Feedback RF
30
8 Benchmarking CBVIR Solutions
31
9 Design Questions
32
10 Summary
34
DESIGNING A CONTENTBASED VIDEO RETRIEVAL SYSTEM
35
2 The Solution
36
31 Shot Boundary Detection
37
32 Scene Boundary Detection
41
42 Highlight Sequences
42
6 Video Browsing Schemes
43
7 Examples of Video Retrieval Systems
44
72 Screening Room
45
73 Virage
46
A SURVEY OF CONTENTBASED IMAGE RETRIEVAL SYSTEMS
47
3 Systems
49
32 AMORE Advanced Multimedia Oriented Retrieval Engine
50
33 ASSERT
51
35 Blobworld
52
36 CANDID Comparison Algorithm for Navigating Digital Image Databases
53
37 Cbird ContentBased Image Retrieval from Digital libraries
54
38 CBVQ ContentBased Visual Query
55
39 Chabot
56
Representation Oriented Management Architecture
57
311 DrawSearch
58
312 FIDS Flexible Image Database System
59
314 FOCUS Fast Object Colorbased Query System
60
315 ImageRETRO Image RETrieval by Reduction and Overview
61
316 ImageRover
63
317 ImageScape
64
318 JACOB Just A COntent Based query system for video databases
65
319 LCPD Leiden 19th Century Portrait Database
66
320 MARS Multimedia Analysis and Retrieval System
67
321 MetaSEEk
69
322 MIR Multimodal Information Retrieval System
70
323 NETRA
71
333 SMURF Similaritybased Multimedia Retrieval Framework
84
334 SQUID Shape Queries Using Image Databases
85
335 Surfimage
86
336 SYNAPSE SYNtactic APpearance Search Engine
87
337 TODAI Typographic Ornament Database And Identification
88
338 VIR Image Engine
89
339 VisualSEEk
90
340 WebSEEk
92
342 WISE Wavelet Image Search Engine
94
4 Summary and Conclusions
99
CASE STUDY MUSE
103
2 The Users Perspective
104
3 The RF Mode
109
32 Probabilistic Model
111
4 The RFC Mode
115
41 More and Better Features
117
42 Clustering
118
43 Learning
119
431 A Numerical Example
123
44 Display Update Strategy
127
5 Experiments and Results
128
51 Testing the System in RF Mode
130
511 Preliminary Tests
131
512 Increasing Database Size
132
513 Improving the ColorBased Feature Set
133
514 Evaluating the Influence of the Number of Images per Iteration
134
515 Testing the Relationship Between the Users Style and System Performance
135
52 Testing Features and Distance Measurements
136
521 Goals and Methodology
137
522 ColorBased Methods
140
523 Shape or Texture Only
141
525 Distance Measures
142
53 Testing the Clustering Algorithm
143
54 Testing the System in RFC Mode
148
542 Tests Using a Small Database
150
543 Increasing Database Size
152
55 Mixed Mode Tests
153
6 Summary
156
7 Future Work
159
References
163
Index
181
Copyright

Other editions - View all

Common terms and phrases

References to this book