Statistical approach for supervised codeword selection

Kihong Park; Seungchul Ryu; Seungryong Kim; Kwanghoon Sohn

doi:10.1117/12.2078771

Statistical approach for supervised codeword selection

Kihong Park, Seungchul Ryu, Seungryong Kim, Kwanghoon Sohn

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Bag-of-words (BoW) is one of the most successful methods for object categorization. This paper proposes a statistical codeword selection algorithm where the best subset is selected from the initial codewords based on the statistical characteristics of codewords. For this purpose, we defined two types of codeword-confidences: cross- and within-category confidences. The cross- and within-category confidences eliminate indistinctive codewords across categories and inconsistent codewords within each category, respectively. An informative subset of codewords is then selected based on these two codeword-confidences. The experimental evaluation for a scene categorization dataset and a Caltech-101 dataset shows that the proposed method improves the categorization performance up to 10% in terms of error rate reduction when cooperated with BoW, sparse coding (SC), and locality-constrained liner coding (LLC). Furthermore, the codeword size is reduced by 50% leading a low computational complexity.

Original language	English
Title of host publication	Proceedings of SPIE-IS and T Electronic Imaging - Intelligent Robots and Computer Vision XXXII
Subtitle of host publication	Algorithms and Techniques
Editors	Juha Roning, David Casasent
Publisher	SPIE
ISBN (Electronic)	9781628414967
DOIs	https://doi.org/10.1117/12.2078771
Publication status	Published - 2015
Event	Intelligent Robots and Computer Vision XXXII: Algorithms and Techniques - San Francisco, United States Duration: 2015 Feb 9 → 2015 Feb 10

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	9406
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Other

Other	Intelligent Robots and Computer Vision XXXII: Algorithms and Techniques
Country/Territory	United States
City	San Francisco
Period	15/2/9 → 15/2/10

Bibliographical note

Publisher Copyright:
© 2015 SPIE-IS&T.

All Science Journal Classification (ASJC) codes

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.2078771

Cite this

Park, K., Ryu, S., Kim, S., & Sohn, K. (2015). Statistical approach for supervised codeword selection. In J. Roning, & D. Casasent (Eds.), Proceedings of SPIE-IS and T Electronic Imaging - Intelligent Robots and Computer Vision XXXII: Algorithms and Techniques [940609] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 9406). SPIE. https://doi.org/10.1117/12.2078771

Park, Kihong ; Ryu, Seungchul ; Kim, Seungryong ; Sohn, Kwanghoon. / Statistical approach for supervised codeword selection. Proceedings of SPIE-IS and T Electronic Imaging - Intelligent Robots and Computer Vision XXXII: Algorithms and Techniques. editor / Juha Roning ; David Casasent. SPIE, 2015. (Proceedings of SPIE - The International Society for Optical Engineering).

@inproceedings{f5064d1b50984e9e809ce82eb901a49c,

title = "Statistical approach for supervised codeword selection",

abstract = "Bag-of-words (BoW) is one of the most successful methods for object categorization. This paper proposes a statistical codeword selection algorithm where the best subset is selected from the initial codewords based on the statistical characteristics of codewords. For this purpose, we defined two types of codeword-confidences: cross- and within-category confidences. The cross- and within-category confidences eliminate indistinctive codewords across categories and inconsistent codewords within each category, respectively. An informative subset of codewords is then selected based on these two codeword-confidences. The experimental evaluation for a scene categorization dataset and a Caltech-101 dataset shows that the proposed method improves the categorization performance up to 10% in terms of error rate reduction when cooperated with BoW, sparse coding (SC), and locality-constrained liner coding (LLC). Furthermore, the codeword size is reduced by 50% leading a low computational complexity.",

author = "Kihong Park and Seungchul Ryu and Seungryong Kim and Kwanghoon Sohn",

note = "Publisher Copyright: {\textcopyright} 2015 SPIE-IS&T.; Intelligent Robots and Computer Vision XXXII: Algorithms and Techniques ; Conference date: 09-02-2015 Through 10-02-2015",

year = "2015",

doi = "10.1117/12.2078771",

language = "English",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Juha Roning and David Casasent",

booktitle = "Proceedings of SPIE-IS and T Electronic Imaging - Intelligent Robots and Computer Vision XXXII",

address = "United States",

}

Park, K, Ryu, S, Kim, S & Sohn, K 2015, Statistical approach for supervised codeword selection. in J Roning & D Casasent (eds), Proceedings of SPIE-IS and T Electronic Imaging - Intelligent Robots and Computer Vision XXXII: Algorithms and Techniques., 940609, Proceedings of SPIE - The International Society for Optical Engineering, vol. 9406, SPIE, Intelligent Robots and Computer Vision XXXII: Algorithms and Techniques, San Francisco, United States, 15/2/9. https://doi.org/10.1117/12.2078771

Statistical approach for supervised codeword selection. / Park, Kihong; Ryu, Seungchul; Kim, Seungryong; Sohn, Kwanghoon.

Proceedings of SPIE-IS and T Electronic Imaging - Intelligent Robots and Computer Vision XXXII: Algorithms and Techniques. ed. / Juha Roning; David Casasent. SPIE, 2015. 940609 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 9406).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Statistical approach for supervised codeword selection

AU - Park, Kihong

AU - Ryu, Seungchul

AU - Kim, Seungryong

AU - Sohn, Kwanghoon

PY - 2015

Y1 - 2015

N2 - Bag-of-words (BoW) is one of the most successful methods for object categorization. This paper proposes a statistical codeword selection algorithm where the best subset is selected from the initial codewords based on the statistical characteristics of codewords. For this purpose, we defined two types of codeword-confidences: cross- and within-category confidences. The cross- and within-category confidences eliminate indistinctive codewords across categories and inconsistent codewords within each category, respectively. An informative subset of codewords is then selected based on these two codeword-confidences. The experimental evaluation for a scene categorization dataset and a Caltech-101 dataset shows that the proposed method improves the categorization performance up to 10% in terms of error rate reduction when cooperated with BoW, sparse coding (SC), and locality-constrained liner coding (LLC). Furthermore, the codeword size is reduced by 50% leading a low computational complexity.

AB - Bag-of-words (BoW) is one of the most successful methods for object categorization. This paper proposes a statistical codeword selection algorithm where the best subset is selected from the initial codewords based on the statistical characteristics of codewords. For this purpose, we defined two types of codeword-confidences: cross- and within-category confidences. The cross- and within-category confidences eliminate indistinctive codewords across categories and inconsistent codewords within each category, respectively. An informative subset of codewords is then selected based on these two codeword-confidences. The experimental evaluation for a scene categorization dataset and a Caltech-101 dataset shows that the proposed method improves the categorization performance up to 10% in terms of error rate reduction when cooperated with BoW, sparse coding (SC), and locality-constrained liner coding (LLC). Furthermore, the codeword size is reduced by 50% leading a low computational complexity.

UR - http://www.scopus.com/inward/record.url?scp=84923673668&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923673668&partnerID=8YFLogxK

U2 - 10.1117/12.2078771

DO - 10.1117/12.2078771

M3 - Conference contribution

AN - SCOPUS:84923673668

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Proceedings of SPIE-IS and T Electronic Imaging - Intelligent Robots and Computer Vision XXXII

A2 - Roning, Juha

A2 - Casasent, David

PB - SPIE

T2 - Intelligent Robots and Computer Vision XXXII: Algorithms and Techniques

Y2 - 9 February 2015 through 10 February 2015

ER -

Park K, Ryu S, Kim S, Sohn K. Statistical approach for supervised codeword selection. In Roning J, Casasent D, editors, Proceedings of SPIE-IS and T Electronic Imaging - Intelligent Robots and Computer Vision XXXII: Algorithms and Techniques. SPIE. 2015. 940609. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2078771

Statistical approach for supervised codeword selection

Abstract

Publication series

Other

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this