A Composite Illumination Invariant Color Feature and Its Application to Partial Image Matching

Masaki KOBAYASHI; Keisuke KAMEYAMA

doi:10.1587/transinf.E95.D.2522

A Composite Illumination Invariant Color Feature and Its Application to Partial Image Matching

Masaki KOBAYASHI, Keisuke KAMEYAMA

Full Text Views

0

Share
Cite this

Summary :

In camera-based object recognition and classification, surface color is one of the most important characteristics. However, apparent object color may differ significantly according to the illumination and surface conditions. Such a variation can be an obstacle in utilizing color features. Geusebroek et al.'s color invariants can be a powerful tool for characterizing the object color regardless of illumination and surface conditions. In this work, we analyze the estimation process of the color invariants from RGB images, and propose a novel invariant feature of color based on the elementary invariants to meet the circular continuity residing in the mapping between colors and their invariants. Experiments show that the use of the proposed invariant in combination with luminance, contributes to improve the retrieval performances of partial object image matching under varying illumination conditions.

Publication: IEICE TRANSACTIONS on Information Vol.E95-D No.10 pp.2522-2532

Publication Date: 2012/10/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E95.D.2522

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Cite this

Copy

Masaki KOBAYASHI, Keisuke KAMEYAMA, "A Composite Illumination Invariant Color Feature and Its Application to Partial Image Matching" in IEICE TRANSACTIONS on Information, vol. E95-D, no. 10, pp. 2522-2532, October 2012, doi: 10.1587/transinf.E95.D.2522.
Abstract: In camera-based object recognition and classification, surface color is one of the most important characteristics. However, apparent object color may differ significantly according to the illumination and surface conditions. Such a variation can be an obstacle in utilizing color features. Geusebroek et al.'s color invariants can be a powerful tool for characterizing the object color regardless of illumination and surface conditions. In this work, we analyze the estimation process of the color invariants from RGB images, and propose a novel invariant feature of color based on the elementary invariants to meet the circular continuity residing in the mapping between colors and their invariants. Experiments show that the use of the proposed invariant in combination with luminance, contributes to improve the retrieval performances of partial object image matching under varying illumination conditions.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E95.D.2522/_p

Copy

@ARTICLE{e95-d_10_2522,
author={Masaki KOBAYASHI, Keisuke KAMEYAMA, },
journal={IEICE TRANSACTIONS on Information},
title={A Composite Illumination Invariant Color Feature and Its Application to Partial Image Matching},
year={2012},
volume={E95-D},
number={10},
pages={2522-2532},
abstract={In camera-based object recognition and classification, surface color is one of the most important characteristics. However, apparent object color may differ significantly according to the illumination and surface conditions. Such a variation can be an obstacle in utilizing color features. Geusebroek et al.'s color invariants can be a powerful tool for characterizing the object color regardless of illumination and surface conditions. In this work, we analyze the estimation process of the color invariants from RGB images, and propose a novel invariant feature of color based on the elementary invariants to meet the circular continuity residing in the mapping between colors and their invariants. Experiments show that the use of the proposed invariant in combination with luminance, contributes to improve the retrieval performances of partial object image matching under varying illumination conditions.},
keywords={},
doi={10.1587/transinf.E95.D.2522},
ISSN={1745-1361},
month={October},}

Copy

TY - JOUR
TI - A Composite Illumination Invariant Color Feature and Its Application to Partial Image Matching
T2 - IEICE TRANSACTIONS on Information
SP - 2522
EP - 2532
AU - Masaki KOBAYASHI
AU - Keisuke KAMEYAMA
PY - 2012
DO - 10.1587/transinf.E95.D.2522
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2012
AB - In camera-based object recognition and classification, surface color is one of the most important characteristics. However, apparent object color may differ significantly according to the illumination and surface conditions. Such a variation can be an obstacle in utilizing color features. Geusebroek et al.'s color invariants can be a powerful tool for characterizing the object color regardless of illumination and surface conditions. In this work, we analyze the estimation process of the color invariants from RGB images, and propose a novel invariant feature of color based on the elementary invariants to meet the circular continuity residing in the mapping between colors and their invariants. Experiments show that the use of the proposed invariant in combination with luminance, contributes to improve the retrieval performances of partial object image matching under varying illumination conditions.
ER -