Light field distortion feature for transparent object recognition

Kazuki Maeno, Hajime Nagahara, Atsushi Shimada, Rin Ichiro Taniguchi

研究成果: ジャーナルへの寄稿Conference article

32 引用 (Scopus)

抄録

Current object-recognition algorithms use local features, such as scale-invariant feature transform (SIFT) and speeded-up robust features (SURF), for visually learning to recognize objects. These approaches though cannot apply to transparent objects made of glass or plastic, as such objects take on the visual features of background objects, and the appearance of such objects dramatically varies with changes in scene background. Indeed, in transmitting light, transparent objects have the unique characteristic of distorting the background by refraction. In this paper, we use a single-shot light field image as an input and model the distortion of the light field caused by the refractive property of a transparent object. We propose a new feature, called the light field distortion (LFD) feature, for identifying a transparent object. The proposal incorporates this LFD feature into the bag-of-features approach for recognizing transparent objects. We evaluated its performance in laboratory and real settings.

元の言語英語
記事番号6619203
ページ(範囲)2786-2793
ページ数8
ジャーナルProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOI
出版物ステータス出版済み - 11 15 2013
イベント26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013 - Portland, OR, 米国
継続期間: 6 23 20136 28 2013

Fingerprint

Object recognition
Refraction
Plastics
Glass

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

これを引用

@article{1eafbe0288c2473d815cdc9db6f6b756,
title = "Light field distortion feature for transparent object recognition",
abstract = "Current object-recognition algorithms use local features, such as scale-invariant feature transform (SIFT) and speeded-up robust features (SURF), for visually learning to recognize objects. These approaches though cannot apply to transparent objects made of glass or plastic, as such objects take on the visual features of background objects, and the appearance of such objects dramatically varies with changes in scene background. Indeed, in transmitting light, transparent objects have the unique characteristic of distorting the background by refraction. In this paper, we use a single-shot light field image as an input and model the distortion of the light field caused by the refractive property of a transparent object. We propose a new feature, called the light field distortion (LFD) feature, for identifying a transparent object. The proposal incorporates this LFD feature into the bag-of-features approach for recognizing transparent objects. We evaluated its performance in laboratory and real settings.",
author = "Kazuki Maeno and Hajime Nagahara and Atsushi Shimada and Taniguchi, {Rin Ichiro}",
year = "2013",
month = "11",
day = "15",
doi = "10.1109/CVPR.2013.359",
language = "English",
pages = "2786--2793",
journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
issn = "1063-6919",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - Light field distortion feature for transparent object recognition

AU - Maeno, Kazuki

AU - Nagahara, Hajime

AU - Shimada, Atsushi

AU - Taniguchi, Rin Ichiro

PY - 2013/11/15

Y1 - 2013/11/15

N2 - Current object-recognition algorithms use local features, such as scale-invariant feature transform (SIFT) and speeded-up robust features (SURF), for visually learning to recognize objects. These approaches though cannot apply to transparent objects made of glass or plastic, as such objects take on the visual features of background objects, and the appearance of such objects dramatically varies with changes in scene background. Indeed, in transmitting light, transparent objects have the unique characteristic of distorting the background by refraction. In this paper, we use a single-shot light field image as an input and model the distortion of the light field caused by the refractive property of a transparent object. We propose a new feature, called the light field distortion (LFD) feature, for identifying a transparent object. The proposal incorporates this LFD feature into the bag-of-features approach for recognizing transparent objects. We evaluated its performance in laboratory and real settings.

AB - Current object-recognition algorithms use local features, such as scale-invariant feature transform (SIFT) and speeded-up robust features (SURF), for visually learning to recognize objects. These approaches though cannot apply to transparent objects made of glass or plastic, as such objects take on the visual features of background objects, and the appearance of such objects dramatically varies with changes in scene background. Indeed, in transmitting light, transparent objects have the unique characteristic of distorting the background by refraction. In this paper, we use a single-shot light field image as an input and model the distortion of the light field caused by the refractive property of a transparent object. We propose a new feature, called the light field distortion (LFD) feature, for identifying a transparent object. The proposal incorporates this LFD feature into the bag-of-features approach for recognizing transparent objects. We evaluated its performance in laboratory and real settings.

UR - http://www.scopus.com/inward/record.url?scp=84887350993&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887350993&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2013.359

DO - 10.1109/CVPR.2013.359

M3 - Conference article

AN - SCOPUS:84887350993

SP - 2786

EP - 2793

JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SN - 1063-6919

M1 - 6619203

ER -