Recognition of Plural Grouping Patterns in Trademarks for CBIR According to the Gestalt Psychology

Koji ABE; Hiromasa IGUCHI; Haiyan TIAN; Debabrata ROY

doi:10.1093/ietisy/e89-d.6.1798

Recognition of Plural Grouping Patterns in Trademarks for CBIR According to the Gestalt Psychology

Koji ABE, Hiromasa IGUCHI, Haiyan TIAN, Debabrata ROY

Full Text Views

0

Share
Cite this

Summary :

According to the Gestalt principals, this paper presents a recognition method of grouping areas in trademark images modeling features for measuring the attraction degree between couples of image components. This investigation would be used for content-based image retrieval from the view of mirroring human perception for images. Depending on variability in human perception for trademark images, the proposed method finds grouping areas by calculating Mahalanobis distance with the features to every combination of two components in images. The features are extracted from every combination of two components in images, and the features represent proximity, shape similarity, and closure between two components. In addition, changing combination of the features, plural grouping patterns are output. Besides, this paper shows the efficiency and limits of the proposed method from experimental results. In the experiments, 104 participants have perceived grouping patterns to 74 trademark images and the human perceptions have been compared with outputs by the proposed method for the 74 images.

Publication: IEICE TRANSACTIONS on Information Vol.E89-D No.6 pp.1798-1805

Publication Date: 2006/06/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e89-d.6.1798

Type of Manuscript: Special Section PAPER (Special Section on Human Communication II)

Category: Vision and Image

Cite this

Copy

Koji ABE, Hiromasa IGUCHI, Haiyan TIAN, Debabrata ROY, "Recognition of Plural Grouping Patterns in Trademarks for CBIR According to the Gestalt Psychology" in IEICE TRANSACTIONS on Information, vol. E89-D, no. 6, pp. 1798-1805, June 2006, doi: 10.1093/ietisy/e89-d.6.1798.
Abstract: According to the Gestalt principals, this paper presents a recognition method of grouping areas in trademark images modeling features for measuring the attraction degree between couples of image components. This investigation would be used for content-based image retrieval from the view of mirroring human perception for images. Depending on variability in human perception for trademark images, the proposed method finds grouping areas by calculating Mahalanobis distance with the features to every combination of two components in images. The features are extracted from every combination of two components in images, and the features represent proximity, shape similarity, and closure between two components. In addition, changing combination of the features, plural grouping patterns are output. Besides, this paper shows the efficiency and limits of the proposed method from experimental results. In the experiments, 104 participants have perceived grouping patterns to 74 trademark images and the human perceptions have been compared with outputs by the proposed method for the 74 images.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.6.1798/_p

Copy

@ARTICLE{e89-d_6_1798,
author={Koji ABE, Hiromasa IGUCHI, Haiyan TIAN, Debabrata ROY, },
journal={IEICE TRANSACTIONS on Information},
title={Recognition of Plural Grouping Patterns in Trademarks for CBIR According to the Gestalt Psychology},
year={2006},
volume={E89-D},
number={6},
pages={1798-1805},
abstract={According to the Gestalt principals, this paper presents a recognition method of grouping areas in trademark images modeling features for measuring the attraction degree between couples of image components. This investigation would be used for content-based image retrieval from the view of mirroring human perception for images. Depending on variability in human perception for trademark images, the proposed method finds grouping areas by calculating Mahalanobis distance with the features to every combination of two components in images. The features are extracted from every combination of two components in images, and the features represent proximity, shape similarity, and closure between two components. In addition, changing combination of the features, plural grouping patterns are output. Besides, this paper shows the efficiency and limits of the proposed method from experimental results. In the experiments, 104 participants have perceived grouping patterns to 74 trademark images and the human perceptions have been compared with outputs by the proposed method for the 74 images.},
keywords={},
doi={10.1093/ietisy/e89-d.6.1798},
ISSN={1745-1361},
month={June},}

Copy

TY - JOUR
TI - Recognition of Plural Grouping Patterns in Trademarks for CBIR According to the Gestalt Psychology
T2 - IEICE TRANSACTIONS on Information
SP - 1798
EP - 1805
AU - Koji ABE
AU - Hiromasa IGUCHI
AU - Haiyan TIAN
AU - Debabrata ROY
PY - 2006
DO - 10.1093/ietisy/e89-d.6.1798
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2006
AB - According to the Gestalt principals, this paper presents a recognition method of grouping areas in trademark images modeling features for measuring the attraction degree between couples of image components. This investigation would be used for content-based image retrieval from the view of mirroring human perception for images. Depending on variability in human perception for trademark images, the proposed method finds grouping areas by calculating Mahalanobis distance with the features to every combination of two components in images. The features are extracted from every combination of two components in images, and the features represent proximity, shape similarity, and closure between two components. In addition, changing combination of the features, plural grouping patterns are output. Besides, this paper shows the efficiency and limits of the proposed method from experimental results. In the experiments, 104 participants have perceived grouping patterns to 74 trademark images and the human perceptions have been compared with outputs by the proposed method for the 74 images.
ER -