Light field distortion feature for transparent object classification

Yichao Xu, Kazuki Maeno, Hajime Nagahara, Atsushi Shimada, Rin Ichiro Aniguchi

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Local features, such as scale-invariant feature transform (SIFT) and speeded up robust features (SURF), are widely used for describing an object in the applications of visual object recognition and classification. However, these approaches cannot apply to transparent objects made of glass or plastic, as such objects take on the visual features of background scenes, and the appearance of such objects dramatically varies with changes in the scenes. Indeed, transparent objects have the unique characteristic of distorting the background by refraction. In this paper, we use a single-shot light field image as input and model the distortion of the light field caused by the refractive property of a transparent object. We propose a new feature which is called the light field distortion (LFD) feature. The proposed feature is background-invariant so that it is able to describe a transparent object without knowing the texture of the scene. The proposal incorporates this LFD feature into the bag-of-features approach for classifying transparent objects. We evaluated its performance and analyzed the limitations in various settings.

Original languageEnglish
Pages (from-to)122-135
Number of pages14
JournalComputer Vision and Image Understanding
Volume139
DOIs
Publication statusPublished - Aug 22 2015

Fingerprint

Object recognition
Refraction
Textures
Plastics
Glass

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Light field distortion feature for transparent object classification. / Xu, Yichao; Maeno, Kazuki; Nagahara, Hajime; Shimada, Atsushi; Aniguchi, Rin Ichiro.

In: Computer Vision and Image Understanding, Vol. 139, 22.08.2015, p. 122-135.

Research output: Contribution to journalArticle

Xu, Yichao ; Maeno, Kazuki ; Nagahara, Hajime ; Shimada, Atsushi ; Aniguchi, Rin Ichiro. / Light field distortion feature for transparent object classification. In: Computer Vision and Image Understanding. 2015 ; Vol. 139. pp. 122-135.
@article{42b4e8a16d784d3cbabc8a4d4b0be306,
title = "Light field distortion feature for transparent object classification",
abstract = "Local features, such as scale-invariant feature transform (SIFT) and speeded up robust features (SURF), are widely used for describing an object in the applications of visual object recognition and classification. However, these approaches cannot apply to transparent objects made of glass or plastic, as such objects take on the visual features of background scenes, and the appearance of such objects dramatically varies with changes in the scenes. Indeed, transparent objects have the unique characteristic of distorting the background by refraction. In this paper, we use a single-shot light field image as input and model the distortion of the light field caused by the refractive property of a transparent object. We propose a new feature which is called the light field distortion (LFD) feature. The proposed feature is background-invariant so that it is able to describe a transparent object without knowing the texture of the scene. The proposal incorporates this LFD feature into the bag-of-features approach for classifying transparent objects. We evaluated its performance and analyzed the limitations in various settings.",
author = "Yichao Xu and Kazuki Maeno and Hajime Nagahara and Atsushi Shimada and Aniguchi, {Rin Ichiro}",
year = "2015",
month = "8",
day = "22",
doi = "10.1016/j.cviu.2015.02.009",
language = "English",
volume = "139",
pages = "122--135",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Light field distortion feature for transparent object classification

AU - Xu, Yichao

AU - Maeno, Kazuki

AU - Nagahara, Hajime

AU - Shimada, Atsushi

AU - Aniguchi, Rin Ichiro

PY - 2015/8/22

Y1 - 2015/8/22

N2 - Local features, such as scale-invariant feature transform (SIFT) and speeded up robust features (SURF), are widely used for describing an object in the applications of visual object recognition and classification. However, these approaches cannot apply to transparent objects made of glass or plastic, as such objects take on the visual features of background scenes, and the appearance of such objects dramatically varies with changes in the scenes. Indeed, transparent objects have the unique characteristic of distorting the background by refraction. In this paper, we use a single-shot light field image as input and model the distortion of the light field caused by the refractive property of a transparent object. We propose a new feature which is called the light field distortion (LFD) feature. The proposed feature is background-invariant so that it is able to describe a transparent object without knowing the texture of the scene. The proposal incorporates this LFD feature into the bag-of-features approach for classifying transparent objects. We evaluated its performance and analyzed the limitations in various settings.

AB - Local features, such as scale-invariant feature transform (SIFT) and speeded up robust features (SURF), are widely used for describing an object in the applications of visual object recognition and classification. However, these approaches cannot apply to transparent objects made of glass or plastic, as such objects take on the visual features of background scenes, and the appearance of such objects dramatically varies with changes in the scenes. Indeed, transparent objects have the unique characteristic of distorting the background by refraction. In this paper, we use a single-shot light field image as input and model the distortion of the light field caused by the refractive property of a transparent object. We propose a new feature which is called the light field distortion (LFD) feature. The proposed feature is background-invariant so that it is able to describe a transparent object without knowing the texture of the scene. The proposal incorporates this LFD feature into the bag-of-features approach for classifying transparent objects. We evaluated its performance and analyzed the limitations in various settings.

UR - http://www.scopus.com/inward/record.url?scp=84939809967&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939809967&partnerID=8YFLogxK

U2 - 10.1016/j.cviu.2015.02.009

DO - 10.1016/j.cviu.2015.02.009

M3 - Article

AN - SCOPUS:84939809967

VL - 139

SP - 122

EP - 135

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

ER -