Image database querying using a multi-scale localized color representation

被引：4

作者：

Gargi, U ^{[1
]}

Kasturi, R ^{[1
]}

机构：

[1] Penn State Univ, Dept Comp Sci & Engn, Ulhasnagar 16802, Maharashtra, India

来源：

IEEE WORKSHOP ON CONTENT-BASED ACCESS OF IMAGE AND VIDEO LIBRARIES (CBAIVL'99) - PROCEEDINGS | 1999年

关键词：

D O I：

10.1109/IVL.1999.781119

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

A computationally efficient method to encode the spatial concentration of colors in images based on local histogram intersection is introduced. The representation allows image matching at multiple resolutions and partial matching of image regions without requiring image segmentation or cluster approximations. The method has been tested on a heterogeneous database of 16,643 images and video frames. Results of objective evaluation using manually selected ground-truth image queries as well as ground-truth video keyframe queries are presented.

引用

页码：28 / 32

页数：5

共 9 条

[1]

[Anonymous], P IEEE C COMP VIS PA

[2] Indexing flowers by color names using domain knowledge-driven segmentation [J].

Das, M ;

Manmatha, R ;

Riseman, EM .

FOURTH IEEE WORKSHOP ON APPLICATIONS OF COMPUTER VISION - WACV'98, PROCEEDINGS, 1998, :94-99

[3] FOCUS: Searching for multi-colored objects in a diverse image database [J].

Das, M ;

Riseman, EM ;

Draper, BA .

1997 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1997, :756-761

[4]

HACHIMURA K, 1996, INT C PATT REC IAPR, V3, P130

[5] Percentile blobs for image similarity [J].

Howe, NR .

IEEE WORKSHOP ON CONTENT-BASED ACCESS OF IMAGE AND VIDEO LIBRARIES - PROCEEDINGS, 1998, :78-83

[6]

Hsu W., 1995, P 3 ACM INT C MULTIM, P305

[7]

PASS G, 1996, ACM INT C MULT NOV

[8]

SMITH JR, 1998, WORKSH CONT BAS ACC

[9]

Swain Micheal j, 1993, SPIE P, V1908, P95

← 1 →