Locality preserving clustering for image database

Xin Zheng; Deng Cai; Xiaofei He; Wei-Ying Ma; Xueyin Lin

doi:10.1145/1027527.1027731

Locality preserving clustering for image database

Xin Zheng
, Deng Cai
, Xiaofei He
, Wei-Ying Ma
, Xueyin Lin

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

84 Citations (Scopus)

Abstract

It is important and challenging to make the growing image repositories easy to search and browse. Image clustering is a technique that helps in several ways, including image data preprocessing, user interface designing, and search result representation. Spectral clustering method has been one of the most promising clustering methods in the last few years, because it can cluster data with complex structure, and the (near) global optimum is guaranteed. However, existing spectral clustering algorithms, like Normalized Cut, are difficult to handle data points out of training set. In this paper, we propose a clustering algorithm named Locality Preserving Clustering (LPC), which shares many of the data representation properties of nonlinear spectral method. Yet LPC provides an explicit mapping function which is defined everywhere, both on training data points and testing points. Experimental results show that LPC is more accurate than both "direct Kmeans" and "PCA + Kmeans". We also show that LPC produces in general comparable results with Normalized Cut, yet is more efficient than Normalized Cut.
Copyright 2004 ACM

Original language	English
Title of host publication	ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia
Publisher	Association for Computing Machinery
Pages	885-891
ISBN (Print)	1581138938, 9781581138931
DOIs	https://doi.org/10.1145/1027527.1027731
Publication status	Published - 2004
Externally published	Yes
Event	ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia - New York, NY, United States Duration: 10 Oct 2004 → 16 Oct 2004

Publication series

Name	ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia

Conference

Conference	ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia
Place	United States
City	New York, NY
Period	10/10/04 → 16/10/04

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Research Keywords

Image clustering
Locality preserving clustering
Locality preserving projections
Spectral clustering

Access Output

10.1145/1027527.1027731

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Zheng, X., Cai, D., He, X., Ma, W.-Y., & Lin, X. (2004). Locality preserving clustering for image database. In ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia (pp. 885-891). (ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia). Association for Computing Machinery. https://doi.org/10.1145/1027527.1027731

@inproceedings{d593224f023b456ebf05d37ce07a4302,

title = "Locality preserving clustering for image database",

abstract = "It is important and challenging to make the growing image repositories easy to search and browse. Image clustering is a technique that helps in several ways, including image data preprocessing, user interface designing, and search result representation. Spectral clustering method has been one of the most promising clustering methods in the last few years, because it can cluster data with complex structure, and the (near) global optimum is guaranteed. However, existing spectral clustering algorithms, like Normalized Cut, are difficult to handle data points out of training set. In this paper, we propose a clustering algorithm named Locality Preserving Clustering (LPC), which shares many of the data representation properties of nonlinear spectral method. Yet LPC provides an explicit mapping function which is defined everywhere, both on training data points and testing points. Experimental results show that LPC is more accurate than both {"}direct Kmeans{"} and {"}PCA + Kmeans{"}. We also show that LPC produces in general comparable results with Normalized Cut, yet is more efficient than Normalized Cut. Copyright 2004 ACM",

keywords = "Image clustering, Locality preserving clustering, Locality preserving projections, Spectral clustering",

author = "Xin Zheng and Deng Cai and Xiaofei He and Wei-Ying Ma and Xueyin Lin",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].; ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia ; Conference date: 10-10-2004 Through 16-10-2004",

year = "2004",

doi = "10.1145/1027527.1027731",

language = "English",

isbn = "1581138938",

series = "ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia",

publisher = "Association for Computing Machinery",

pages = "885--891",

booktitle = "ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia",

address = "United States",

}

Zheng, X, Cai, D, He, X, Ma, W-Y & Lin, X 2004, Locality preserving clustering for image database. in ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia. ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia, Association for Computing Machinery, pp. 885-891, ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia, New York, NY, United States, 10/10/04. https://doi.org/10.1145/1027527.1027731

Locality preserving clustering for image database. / Zheng, Xin; Cai, Deng; He, Xiaofei et al.
ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia. Association for Computing Machinery, 2004. p. 885-891 (ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Locality preserving clustering for image database

AU - Zheng, Xin

AU - Cai, Deng

AU - He, Xiaofei

AU - Ma, Wei-Ying

AU - Lin, Xueyin

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2004

Y1 - 2004

N2 - It is important and challenging to make the growing image repositories easy to search and browse. Image clustering is a technique that helps in several ways, including image data preprocessing, user interface designing, and search result representation. Spectral clustering method has been one of the most promising clustering methods in the last few years, because it can cluster data with complex structure, and the (near) global optimum is guaranteed. However, existing spectral clustering algorithms, like Normalized Cut, are difficult to handle data points out of training set. In this paper, we propose a clustering algorithm named Locality Preserving Clustering (LPC), which shares many of the data representation properties of nonlinear spectral method. Yet LPC provides an explicit mapping function which is defined everywhere, both on training data points and testing points. Experimental results show that LPC is more accurate than both "direct Kmeans" and "PCA + Kmeans". We also show that LPC produces in general comparable results with Normalized Cut, yet is more efficient than Normalized Cut. Copyright 2004 ACM

AB - It is important and challenging to make the growing image repositories easy to search and browse. Image clustering is a technique that helps in several ways, including image data preprocessing, user interface designing, and search result representation. Spectral clustering method has been one of the most promising clustering methods in the last few years, because it can cluster data with complex structure, and the (near) global optimum is guaranteed. However, existing spectral clustering algorithms, like Normalized Cut, are difficult to handle data points out of training set. In this paper, we propose a clustering algorithm named Locality Preserving Clustering (LPC), which shares many of the data representation properties of nonlinear spectral method. Yet LPC provides an explicit mapping function which is defined everywhere, both on training data points and testing points. Experimental results show that LPC is more accurate than both "direct Kmeans" and "PCA + Kmeans". We also show that LPC produces in general comparable results with Normalized Cut, yet is more efficient than Normalized Cut. Copyright 2004 ACM

KW - Image clustering

KW - Locality preserving clustering

KW - Locality preserving projections

KW - Spectral clustering

UR - https://www.scopus.com/pages/publications/13444260824

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-13444260824&origin=recordpage

U2 - 10.1145/1027527.1027731

DO - 10.1145/1027527.1027731

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 1581138938

SN - 9781581138931

T3 - ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia

SP - 885

EP - 891

BT - ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia

PB - Association for Computing Machinery

T2 - ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia

Y2 - 10 October 2004 through 16 October 2004

ER -

Locality preserving clustering for image database

Abstract

Publication series

Conference

Bibliographical note

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this