The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dans cet article, nous présentons un nouveau descripteur SIFT basé sur des composants indépendants des couleurs (appelé CIC-SIFT) pour la classification objet/scène. Nous apprenons d'abord une matrice de transformation de couleur efficace basée sur l'analyse de composants indépendants (ICA), qui s'adapte à chaque catégorie d'une base de données. La transformation des couleurs basée sur ICA peut améliorer le contraste entre les objets et l'arrière-plan d'une image. Ensuite, nous calculons les descripteurs CIC-SIFT sur les trois composants transformés indépendants des couleurs. Étant donné que la transformation des couleurs basée sur l'ICA peut améliorer les objets et supprimer l'arrière-plan, le CIC-SIFT proposé peut extraire des caractéristiques locales plus efficaces et plus discriminantes pour la classification objet/scène. La comparaison est effectuée entre sept descripteurs SIFT, et les résultats de la classification expérimentale montrent que notre proposition CIC-SIFT est supérieure aux autres descripteurs SIFT conventionnels.
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.
Copier
Dan-ni AI, Xian-hua HAN, Xiang RUAN, Yen-wei CHEN, "Color Independent Components Based SIFT Descriptors for Object/Scene Classification" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 9, pp. 2577-2586, September 2010, doi: 10.1587/transinf.E93.D.2577.
Abstract: In this paper, we present a novel color independent components based SIFT descriptor (termed CIC-SIFT) for object/scene classification. We first learn an efficient color transformation matrix based on independent component analysis (ICA), which is adaptive to each category in a database. The ICA-based color transformation can enhance contrast between the objects and the background in an image. Then we compute CIC-SIFT descriptors over all three transformed color independent components. Since the ICA-based color transformation can boost the objects and suppress the background, the proposed CIC-SIFT can extract more effective and discriminative local features for object/scene classification. The comparison is performed among seven SIFT descriptors, and the experimental classification results show that our proposed CIC-SIFT is superior to other conventional SIFT descriptors.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.2577/_p
Copier
@ARTICLE{e93-d_9_2577,
author={Dan-ni AI, Xian-hua HAN, Xiang RUAN, Yen-wei CHEN, },
journal={IEICE TRANSACTIONS on Information},
title={Color Independent Components Based SIFT Descriptors for Object/Scene Classification},
year={2010},
volume={E93-D},
number={9},
pages={2577-2586},
abstract={In this paper, we present a novel color independent components based SIFT descriptor (termed CIC-SIFT) for object/scene classification. We first learn an efficient color transformation matrix based on independent component analysis (ICA), which is adaptive to each category in a database. The ICA-based color transformation can enhance contrast between the objects and the background in an image. Then we compute CIC-SIFT descriptors over all three transformed color independent components. Since the ICA-based color transformation can boost the objects and suppress the background, the proposed CIC-SIFT can extract more effective and discriminative local features for object/scene classification. The comparison is performed among seven SIFT descriptors, and the experimental classification results show that our proposed CIC-SIFT is superior to other conventional SIFT descriptors.},
keywords={},
doi={10.1587/transinf.E93.D.2577},
ISSN={1745-1361},
month={September},}
Copier
TY - JOUR
TI - Color Independent Components Based SIFT Descriptors for Object/Scene Classification
T2 - IEICE TRANSACTIONS on Information
SP - 2577
EP - 2586
AU - Dan-ni AI
AU - Xian-hua HAN
AU - Xiang RUAN
AU - Yen-wei CHEN
PY - 2010
DO - 10.1587/transinf.E93.D.2577
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2010
AB - In this paper, we present a novel color independent components based SIFT descriptor (termed CIC-SIFT) for object/scene classification. We first learn an efficient color transformation matrix based on independent component analysis (ICA), which is adaptive to each category in a database. The ICA-based color transformation can enhance contrast between the objects and the background in an image. Then we compute CIC-SIFT descriptors over all three transformed color independent components. Since the ICA-based color transformation can boost the objects and suppress the background, the proposed CIC-SIFT can extract more effective and discriminative local features for object/scene classification. The comparison is performed among seven SIFT descriptors, and the experimental classification results show that our proposed CIC-SIFT is superior to other conventional SIFT descriptors.
ER -