Efficient cloth pattern recognition using random ferns

Inseong Hwang, Seungwoo Jeon, Beobkeun Cho, Yoonsik Choe

Research output: Contribution to journalArticle

Abstract

This paper proposes a novel image classification scheme for cloth pattern recognition. The rotation and scale invariant delta-HOG (DHOG)-based descriptor and the entire recognition process using random ferns with this descriptor are proposed independent from pose and scale changes. These methods consider maximun orientation and various radii of a circular patch window for fast and efficient classification even when cloth patches are rotated and the scale is changed. It exhibits good performance in cloth pattern recognition experiments. It found a greater number of similar cloth patches than dense-SIFT in 20 tests out of a total of 36 query tests. In addition, the proposed method is much faster than dense-SIFT in both training and testing; its time consumption is decreased by 57.7% in training and 41.4% in testing. The proposed method, therefore, is expected to contribute to real-time cloth searching service applications that update vast numbers of cloth images posted on the Internet.

Original languageEnglish
Pages (from-to)475-478
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE98D
Issue number2
DOIs
Publication statusPublished - 2015 Feb 1

Fingerprint

Pattern recognition
Image classification
Testing
Random processes
Internet
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Hwang, Inseong ; Jeon, Seungwoo ; Cho, Beobkeun ; Choe, Yoonsik. / Efficient cloth pattern recognition using random ferns. In: IEICE Transactions on Information and Systems. 2015 ; Vol. E98D, No. 2. pp. 475-478.
@article{4466bed5042840b49ad8eb03074ad270,
title = "Efficient cloth pattern recognition using random ferns",
abstract = "This paper proposes a novel image classification scheme for cloth pattern recognition. The rotation and scale invariant delta-HOG (DHOG)-based descriptor and the entire recognition process using random ferns with this descriptor are proposed independent from pose and scale changes. These methods consider maximun orientation and various radii of a circular patch window for fast and efficient classification even when cloth patches are rotated and the scale is changed. It exhibits good performance in cloth pattern recognition experiments. It found a greater number of similar cloth patches than dense-SIFT in 20 tests out of a total of 36 query tests. In addition, the proposed method is much faster than dense-SIFT in both training and testing; its time consumption is decreased by 57.7{\%} in training and 41.4{\%} in testing. The proposed method, therefore, is expected to contribute to real-time cloth searching service applications that update vast numbers of cloth images posted on the Internet.",
author = "Inseong Hwang and Seungwoo Jeon and Beobkeun Cho and Yoonsik Choe",
year = "2015",
month = "2",
day = "1",
doi = "10.1587/transinf.2014EDL8197",
language = "English",
volume = "E98D",
pages = "475--478",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "2",

}

Efficient cloth pattern recognition using random ferns. / Hwang, Inseong; Jeon, Seungwoo; Cho, Beobkeun; Choe, Yoonsik.

In: IEICE Transactions on Information and Systems, Vol. E98D, No. 2, 01.02.2015, p. 475-478.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Efficient cloth pattern recognition using random ferns

AU - Hwang, Inseong

AU - Jeon, Seungwoo

AU - Cho, Beobkeun

AU - Choe, Yoonsik

PY - 2015/2/1

Y1 - 2015/2/1

N2 - This paper proposes a novel image classification scheme for cloth pattern recognition. The rotation and scale invariant delta-HOG (DHOG)-based descriptor and the entire recognition process using random ferns with this descriptor are proposed independent from pose and scale changes. These methods consider maximun orientation and various radii of a circular patch window for fast and efficient classification even when cloth patches are rotated and the scale is changed. It exhibits good performance in cloth pattern recognition experiments. It found a greater number of similar cloth patches than dense-SIFT in 20 tests out of a total of 36 query tests. In addition, the proposed method is much faster than dense-SIFT in both training and testing; its time consumption is decreased by 57.7% in training and 41.4% in testing. The proposed method, therefore, is expected to contribute to real-time cloth searching service applications that update vast numbers of cloth images posted on the Internet.

AB - This paper proposes a novel image classification scheme for cloth pattern recognition. The rotation and scale invariant delta-HOG (DHOG)-based descriptor and the entire recognition process using random ferns with this descriptor are proposed independent from pose and scale changes. These methods consider maximun orientation and various radii of a circular patch window for fast and efficient classification even when cloth patches are rotated and the scale is changed. It exhibits good performance in cloth pattern recognition experiments. It found a greater number of similar cloth patches than dense-SIFT in 20 tests out of a total of 36 query tests. In addition, the proposed method is much faster than dense-SIFT in both training and testing; its time consumption is decreased by 57.7% in training and 41.4% in testing. The proposed method, therefore, is expected to contribute to real-time cloth searching service applications that update vast numbers of cloth images posted on the Internet.

UR - http://www.scopus.com/inward/record.url?scp=84922339961&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922339961&partnerID=8YFLogxK

U2 - 10.1587/transinf.2014EDL8197

DO - 10.1587/transinf.2014EDL8197

M3 - Article

VL - E98D

SP - 475

EP - 478

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 2

ER -