Image representation for generic object recognition using higher-order local autocorrelation features on posterior probability images

Tetsu Matsukawa, Takio Kurita

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

This paper presents a novel image representation method for generic object recognition by using higher-order local autocorrelations on posterior probability images. The proposed method is an extension of the bag-of-features approach to posterior probability images. The standard bag-of-features approach is approximately thought of as a method that classifies an image to a category whose sum of posterior probabilities on a posterior probability image is maximum. However, by using local autocorrelations of posterior probability images, the proposed method extracts richer information than the standard bag-of-features. Experimental results reveal that the proposed method exhibits higher classification performances than the standard bag-of-features method.

Original languageEnglish
Pages (from-to)707-719
Number of pages13
JournalPattern Recognition
Volume45
Issue number2
DOIs
Publication statusPublished - Feb 1 2012

Fingerprint

Object recognition
Autocorrelation

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Image representation for generic object recognition using higher-order local autocorrelation features on posterior probability images. / Matsukawa, Tetsu; Kurita, Takio.

In: Pattern Recognition, Vol. 45, No. 2, 01.02.2012, p. 707-719.

Research output: Contribution to journalArticle

@article{ecccef888d0d41708a5b489a05ebf6d5,
title = "Image representation for generic object recognition using higher-order local autocorrelation features on posterior probability images",
abstract = "This paper presents a novel image representation method for generic object recognition by using higher-order local autocorrelations on posterior probability images. The proposed method is an extension of the bag-of-features approach to posterior probability images. The standard bag-of-features approach is approximately thought of as a method that classifies an image to a category whose sum of posterior probabilities on a posterior probability image is maximum. However, by using local autocorrelations of posterior probability images, the proposed method extracts richer information than the standard bag-of-features. Experimental results reveal that the proposed method exhibits higher classification performances than the standard bag-of-features method.",
author = "Tetsu Matsukawa and Takio Kurita",
year = "2012",
month = "2",
day = "1",
doi = "10.1016/j.patcog.2011.07.018",
language = "English",
volume = "45",
pages = "707--719",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "2",

}

TY - JOUR

T1 - Image representation for generic object recognition using higher-order local autocorrelation features on posterior probability images

AU - Matsukawa, Tetsu

AU - Kurita, Takio

PY - 2012/2/1

Y1 - 2012/2/1

N2 - This paper presents a novel image representation method for generic object recognition by using higher-order local autocorrelations on posterior probability images. The proposed method is an extension of the bag-of-features approach to posterior probability images. The standard bag-of-features approach is approximately thought of as a method that classifies an image to a category whose sum of posterior probabilities on a posterior probability image is maximum. However, by using local autocorrelations of posterior probability images, the proposed method extracts richer information than the standard bag-of-features. Experimental results reveal that the proposed method exhibits higher classification performances than the standard bag-of-features method.

AB - This paper presents a novel image representation method for generic object recognition by using higher-order local autocorrelations on posterior probability images. The proposed method is an extension of the bag-of-features approach to posterior probability images. The standard bag-of-features approach is approximately thought of as a method that classifies an image to a category whose sum of posterior probabilities on a posterior probability image is maximum. However, by using local autocorrelations of posterior probability images, the proposed method extracts richer information than the standard bag-of-features. Experimental results reveal that the proposed method exhibits higher classification performances than the standard bag-of-features method.

UR - http://www.scopus.com/inward/record.url?scp=80052965805&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052965805&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2011.07.018

DO - 10.1016/j.patcog.2011.07.018

M3 - Article

AN - SCOPUS:80052965805

VL - 45

SP - 707

EP - 719

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 2

ER -