Automatic extraction and recognition of shoe logos with a wide variety of appearance

Kazunori Aoki, Wataru Oyama, Tetsushi Wakabayashi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

A logo is a symbolic presentation that is designed not only to identify a product manufacturer but also to attract the attention of shoppers. Shoe logos are a challenging subject for automatic extraction and recognition using image analysis techniques because they have characteristics that distinguish them from those of other products, that is, there is much variation in the appearance of shoe logos. In this paper, we propose an automatic extraction and recognition method for shoe logos with a wide variety of appearanee using a limited number training samples. The proposed method employs maximally stable extremal regions (MSERs) for the initial region extraction, an iterative algorithm for region grouping, and gradient features and a support vector machine for logo recognition. The results of performance evaluation experiments using a logo dataset that consists of a wide variety of appearance show that the proposed method achieves promising performance for both logo extraction and recognition.

Original languageEnglish
Title of host publicationProceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages211-214
Number of pages4
ISBN (Electronic)9784901122160
DOIs
Publication statusPublished - Jul 19 2017
Externally publishedYes
Event15th IAPR International Conference on Machine Vision Applications, MVA 2017 - Nagoya, Japan
Duration: May 8 2017May 12 2017

Other

Other15th IAPR International Conference on Machine Vision Applications, MVA 2017
CountryJapan
CityNagoya
Period5/8/175/12/17

Fingerprint

Image analysis
Support vector machines
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Aoki, K., Oyama, W., & Wakabayashi, T. (2017). Automatic extraction and recognition of shoe logos with a wide variety of appearance. In Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017 (pp. 211-214). [7986838] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/MVA.2017.7986838

Automatic extraction and recognition of shoe logos with a wide variety of appearance. / Aoki, Kazunori; Oyama, Wataru; Wakabayashi, Tetsushi.

Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 211-214 7986838.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Aoki, K, Oyama, W & Wakabayashi, T 2017, Automatic extraction and recognition of shoe logos with a wide variety of appearance. in Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017., 7986838, Institute of Electrical and Electronics Engineers Inc., pp. 211-214, 15th IAPR International Conference on Machine Vision Applications, MVA 2017, Nagoya, Japan, 5/8/17. https://doi.org/10.23919/MVA.2017.7986838
Aoki K, Oyama W, Wakabayashi T. Automatic extraction and recognition of shoe logos with a wide variety of appearance. In Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 211-214. 7986838 https://doi.org/10.23919/MVA.2017.7986838
Aoki, Kazunori ; Oyama, Wataru ; Wakabayashi, Tetsushi. / Automatic extraction and recognition of shoe logos with a wide variety of appearance. Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 211-214
@inproceedings{f05b9611c08d4b8d8ab258d0118ba24f,
title = "Automatic extraction and recognition of shoe logos with a wide variety of appearance",
abstract = "A logo is a symbolic presentation that is designed not only to identify a product manufacturer but also to attract the attention of shoppers. Shoe logos are a challenging subject for automatic extraction and recognition using image analysis techniques because they have characteristics that distinguish them from those of other products, that is, there is much variation in the appearance of shoe logos. In this paper, we propose an automatic extraction and recognition method for shoe logos with a wide variety of appearanee using a limited number training samples. The proposed method employs maximally stable extremal regions (MSERs) for the initial region extraction, an iterative algorithm for region grouping, and gradient features and a support vector machine for logo recognition. The results of performance evaluation experiments using a logo dataset that consists of a wide variety of appearance show that the proposed method achieves promising performance for both logo extraction and recognition.",
author = "Kazunori Aoki and Wataru Oyama and Tetsushi Wakabayashi",
year = "2017",
month = "7",
day = "19",
doi = "10.23919/MVA.2017.7986838",
language = "English",
pages = "211--214",
booktitle = "Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Automatic extraction and recognition of shoe logos with a wide variety of appearance

AU - Aoki, Kazunori

AU - Oyama, Wataru

AU - Wakabayashi, Tetsushi

PY - 2017/7/19

Y1 - 2017/7/19

N2 - A logo is a symbolic presentation that is designed not only to identify a product manufacturer but also to attract the attention of shoppers. Shoe logos are a challenging subject for automatic extraction and recognition using image analysis techniques because they have characteristics that distinguish them from those of other products, that is, there is much variation in the appearance of shoe logos. In this paper, we propose an automatic extraction and recognition method for shoe logos with a wide variety of appearanee using a limited number training samples. The proposed method employs maximally stable extremal regions (MSERs) for the initial region extraction, an iterative algorithm for region grouping, and gradient features and a support vector machine for logo recognition. The results of performance evaluation experiments using a logo dataset that consists of a wide variety of appearance show that the proposed method achieves promising performance for both logo extraction and recognition.

AB - A logo is a symbolic presentation that is designed not only to identify a product manufacturer but also to attract the attention of shoppers. Shoe logos are a challenging subject for automatic extraction and recognition using image analysis techniques because they have characteristics that distinguish them from those of other products, that is, there is much variation in the appearance of shoe logos. In this paper, we propose an automatic extraction and recognition method for shoe logos with a wide variety of appearanee using a limited number training samples. The proposed method employs maximally stable extremal regions (MSERs) for the initial region extraction, an iterative algorithm for region grouping, and gradient features and a support vector machine for logo recognition. The results of performance evaluation experiments using a logo dataset that consists of a wide variety of appearance show that the proposed method achieves promising performance for both logo extraction and recognition.

UR - http://www.scopus.com/inward/record.url?scp=85027870187&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027870187&partnerID=8YFLogxK

U2 - 10.23919/MVA.2017.7986838

DO - 10.23919/MVA.2017.7986838

M3 - Conference contribution

AN - SCOPUS:85027870187

SP - 211

EP - 214

BT - Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -