Automated separation of reflections from a single image based on edge classification

Hara Kenji, Kohei Inoue, Kiichi Urahama

Research output: Contribution to conferencePaper

Abstract

Looking through a window, the object behind the window is often disturbed by a reflection of another object. In the paper, we present a new method for separating reflections from a single image. Most existing techniques require the programmer to create an image database or require the user to manually provide the position and layer information of feature points in the input image, and thus suffer from being extremely laborious. Our method is realized by classifying edges in the input image based on the belonging layer and formalizing the problem of decomposing the single image into two layer images as an optimization problem easier to solve based on this classification, and then solving this optimization with a pyramid structure and deterministic annealing. As a result, we are able to accomplish almost fully automated separation of reflections from a single image.

Original languageEnglish
Pages18-25
Number of pages8
Publication statusPublished - Dec 1 2007
Event2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007 - Barcelona, Spain
Duration: Mar 8 2007Mar 11 2007

Other

Other2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007
CountrySpain
CityBarcelona
Period3/8/073/11/07

Fingerprint

Annealing

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Kenji, H., Inoue, K., & Urahama, K. (2007). Automated separation of reflections from a single image based on edge classification. 18-25. Paper presented at 2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007, Barcelona, Spain.

Automated separation of reflections from a single image based on edge classification. / Kenji, Hara; Inoue, Kohei; Urahama, Kiichi.

2007. 18-25 Paper presented at 2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007, Barcelona, Spain.

Research output: Contribution to conferencePaper

Kenji, H, Inoue, K & Urahama, K 2007, 'Automated separation of reflections from a single image based on edge classification' Paper presented at 2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007, Barcelona, Spain, 3/8/07 - 3/11/07, pp. 18-25.
Kenji H, Inoue K, Urahama K. Automated separation of reflections from a single image based on edge classification. 2007. Paper presented at 2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007, Barcelona, Spain.
Kenji, Hara ; Inoue, Kohei ; Urahama, Kiichi. / Automated separation of reflections from a single image based on edge classification. Paper presented at 2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007, Barcelona, Spain.8 p.
@conference{df882d5b2d4c4312a66c10855cfea029,
title = "Automated separation of reflections from a single image based on edge classification",
abstract = "Looking through a window, the object behind the window is often disturbed by a reflection of another object. In the paper, we present a new method for separating reflections from a single image. Most existing techniques require the programmer to create an image database or require the user to manually provide the position and layer information of feature points in the input image, and thus suffer from being extremely laborious. Our method is realized by classifying edges in the input image based on the belonging layer and formalizing the problem of decomposing the single image into two layer images as an optimization problem easier to solve based on this classification, and then solving this optimization with a pyramid structure and deterministic annealing. As a result, we are able to accomplish almost fully automated separation of reflections from a single image.",
author = "Hara Kenji and Kohei Inoue and Kiichi Urahama",
year = "2007",
month = "12",
day = "1",
language = "English",
pages = "18--25",
note = "2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007 ; Conference date: 08-03-2007 Through 11-03-2007",

}

TY - CONF

T1 - Automated separation of reflections from a single image based on edge classification

AU - Kenji, Hara

AU - Inoue, Kohei

AU - Urahama, Kiichi

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Looking through a window, the object behind the window is often disturbed by a reflection of another object. In the paper, we present a new method for separating reflections from a single image. Most existing techniques require the programmer to create an image database or require the user to manually provide the position and layer information of feature points in the input image, and thus suffer from being extremely laborious. Our method is realized by classifying edges in the input image based on the belonging layer and formalizing the problem of decomposing the single image into two layer images as an optimization problem easier to solve based on this classification, and then solving this optimization with a pyramid structure and deterministic annealing. As a result, we are able to accomplish almost fully automated separation of reflections from a single image.

AB - Looking through a window, the object behind the window is often disturbed by a reflection of another object. In the paper, we present a new method for separating reflections from a single image. Most existing techniques require the programmer to create an image database or require the user to manually provide the position and layer information of feature points in the input image, and thus suffer from being extremely laborious. Our method is realized by classifying edges in the input image based on the belonging layer and formalizing the problem of decomposing the single image into two layer images as an optimization problem easier to solve based on this classification, and then solving this optimization with a pyramid structure and deterministic annealing. As a result, we are able to accomplish almost fully automated separation of reflections from a single image.

UR - http://www.scopus.com/inward/record.url?scp=67650258001&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650258001&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:67650258001

SP - 18

EP - 25

ER -