Language:
English
繁體中文
Help
回圖書館首頁
手機版館藏查詢
Login
Back
Switch To:
Labeled
|
MARC Mode
|
ISBD
Object and concept recognition for c...
~
Li, Yi.
Linked to FindBook
Google Book
Amazon
博客來
Object and concept recognition for content-based image retrieval.
Record Type:
Electronic resources : Monograph/item
Title/Author:
Object and concept recognition for content-based image retrieval./
Author:
Li, Yi.
Description:
88 p.
Notes:
Source: Dissertation Abstracts International, Volume: 66-02, Section: B, page: 0990.
Contained By:
Dissertation Abstracts International66-02B.
Subject:
Computer Science. -
Online resource:
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3163394
ISBN:
0496976508
Object and concept recognition for content-based image retrieval.
Li, Yi.
Object and concept recognition for content-based image retrieval.
- 88 p.
Source: Dissertation Abstracts International, Volume: 66-02, Section: B, page: 0990.
Thesis (Ph.D.)--University of Washington, 2005.
The problem of recognizing classes of objects in images is important for annotation and indexing of image and video databases. Users of commercial CBIR systems prefer to pose their queries in terms of key words. To help automate the indexing process, we represent images as sets of feature vectors of multiple types of abstract regions, which come from various segmentation processes. With this representation, we have developed two new algorithms to recognize classes of objects and concepts in outdoor photographic scenes. The semi-supervised EM-variant algorithm models each abstract region as a mixture of Gaussian distributions over its feature space. The more powerful generative/discriminative learning algorithm is a two-phase method. The generative phase normalizes the description length of images, which can have an arbitrary number of extracted features. In the discriminative phase, a classifier learns which images, as represented by this fixed-length description, contain the target object. We have tested our approaches by experimenting with several different data sets and combinations of features. Our results showed a significant improvement over the published results.
ISBN: 0496976508Subjects--Topical Terms:
626642
Computer Science.
Object and concept recognition for content-based image retrieval.
LDR
:02043nmm 2200265 4500
001
1849460
005
20051205073952.5
008
130614s2005 eng d
020
$a
0496976508
035
$a
(UnM)AAI3163394
035
$a
AAI3163394
040
$a
UnM
$c
UnM
100
1
$a
Li, Yi.
$3
911053
245
1 0
$a
Object and concept recognition for content-based image retrieval.
300
$a
88 p.
500
$a
Source: Dissertation Abstracts International, Volume: 66-02, Section: B, page: 0990.
500
$a
Chair: Linda G. Shapiro.
502
$a
Thesis (Ph.D.)--University of Washington, 2005.
520
$a
The problem of recognizing classes of objects in images is important for annotation and indexing of image and video databases. Users of commercial CBIR systems prefer to pose their queries in terms of key words. To help automate the indexing process, we represent images as sets of feature vectors of multiple types of abstract regions, which come from various segmentation processes. With this representation, we have developed two new algorithms to recognize classes of objects and concepts in outdoor photographic scenes. The semi-supervised EM-variant algorithm models each abstract region as a mixture of Gaussian distributions over its feature space. The more powerful generative/discriminative learning algorithm is a two-phase method. The generative phase normalizes the description length of images, which can have an arbitrary number of extracted features. In the discriminative phase, a classifier learns which images, as represented by this fixed-length description, contain the target object. We have tested our approaches by experimenting with several different data sets and combinations of features. Our results showed a significant improvement over the published results.
590
$a
School code: 0250.
650
4
$a
Computer Science.
$3
626642
690
$a
0984
710
2 0
$a
University of Washington.
$3
545923
773
0
$t
Dissertation Abstracts International
$g
66-02B.
790
1 0
$a
Shapiro, Linda G.,
$e
advisor
790
$a
0250
791
$a
Ph.D.
792
$a
2005
856
4 0
$u
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3163394
based on 0 review(s)
Location:
ALL
電子資源
Year:
Volume Number:
Items
1 records • Pages 1 •
1
Inventory Number
Location Name
Item Class
Material type
Call number
Usage Class
Loan Status
No. of reservations
Opac note
Attachments
W9198974
電子資源
11.線上閱覽_V
電子書
EB
一般使用(Normal)
On shelf
0
1 records • Pages 1 •
1
Multimedia
Reviews
Add a review
and share your thoughts with other readers
Export
pickup library
Processing
...
Change password
Login