Statistical approach for supervised codeword selection

Kihong Park, Seungchul Ryu, Seungryong Kim, Kwanghoon Sohn

Research output: Chapter in Book/Report/Conference proceedingConference 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 languageEnglish
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Intelligent Robots and Computer Vision XXXII
Subtitle of host publicationAlgorithms and Techniques
EditorsJuha Roning, David Casasent
PublisherSPIE
ISBN (Electronic)9781628414967
DOIs
Publication statusPublished - 2015 Jan 1
EventIntelligent Robots and Computer Vision XXXII: Algorithms and Techniques - San Francisco, United States
Duration: 2015 Feb 92015 Feb 10

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume9406
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Other

OtherIntelligent Robots and Computer Vision XXXII: Algorithms and Techniques
CountryUnited States
CitySan Francisco
Period15/2/915/2/10

Fingerprint

Set theory
Confidence
confidence
Computational complexity
Categorization
bags
set theory
coding
Sparse Coding
Subset
linings
Experimental Evaluation
Locality
Inconsistent
Low Complexity
Error Rate
Computational Complexity
Eliminate
Coding
evaluation

All Science Journal Classification (ASJC) codes

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

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",
year = "2015",
month = "1",
day = "1",
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 proceedingConference contribution

TY - GEN

T1 - Statistical approach for supervised codeword selection

AU - Park, Kihong

AU - Ryu, Seungchul

AU - Kim, Seungryong

AU - Sohn, Kwanghoon

PY - 2015/1/1

Y1 - 2015/1/1

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

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