IEICE TRANSACTIONS on Information
Extraction and Recognition of Shoe Logos with a Wide Variety of Appearance Using Two-Stage Classifiers
Summary :
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 within-class 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 appearance using a limited number of training samples. The proposed method employs maximally stable extremal regions 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 appearances show that the proposed method achieves promising performance for both logo extraction and recognition.
- Publication
- IEICE TRANSACTIONS on Information Vol.E101-D No.5 pp.1325-1332
- Publication Date
- 2018/05/01
- Publicized
- 2018/02/16
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2017MVP0026
- Type of Manuscript
- Special Section PAPER (Special Section on Machine Vision and its Applications)
- Category
- Machine Vision and its Applications
Authors
Kazunori AOKI
Mie University
Wataru OHYAMA
Mie University
Tetsushi WAKABAYASHI
Mie University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Kazunori AOKI, Wataru OHYAMA, Tetsushi WAKABAYASHI, "Extraction and Recognition of Shoe Logos with a Wide Variety of Appearance Using Two-Stage Classifiers" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 5, pp. 1325-1332, May 2018, doi: 10.1587/transinf.2017MVP0026.
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 within-class 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 appearance using a limited number of training samples. The proposed method employs maximally stable extremal regions 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 appearances show that the proposed method achieves promising performance for both logo extraction and recognition.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017MVP0026/_p
Copy
@ARTICLE{e101-d_5_1325,
author={Kazunori AOKI, Wataru OHYAMA, Tetsushi WAKABAYASHI, },
journal={IEICE TRANSACTIONS on Information},
title={Extraction and Recognition of Shoe Logos with a Wide Variety of Appearance Using Two-Stage Classifiers},
year={2018},
volume={E101-D},
number={5},
pages={1325-1332},
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 within-class 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 appearance using a limited number of training samples. The proposed method employs maximally stable extremal regions 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 appearances show that the proposed method achieves promising performance for both logo extraction and recognition.},
keywords={},
doi={10.1587/transinf.2017MVP0026},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Extraction and Recognition of Shoe Logos with a Wide Variety of Appearance Using Two-Stage Classifiers
T2 - IEICE TRANSACTIONS on Information
SP - 1325
EP - 1332
AU - Kazunori AOKI
AU - Wataru OHYAMA
AU - Tetsushi WAKABAYASHI
PY - 2018
DO - 10.1587/transinf.2017MVP0026
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2018
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 within-class 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 appearance using a limited number of training samples. The proposed method employs maximally stable extremal regions 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 appearances show that the proposed method achieves promising performance for both logo extraction and recognition.
ER -
English
