Removal of specular reflections from image sequences using feature correspondences

Syed. M. Z. Abbas Shah, Stephen Marshall, Paul Murray

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The presence of specular highlights can hide underlying features of a scene within an image and can be problematic in many application scenarios. In particular, this poses a significant challenge for applications where image stitching is used to create a single static image of a scene from inspection footage of pipes, gas tubes, train tracks and concrete structures. Furthermore, they can hide small defects in the images causing them to be missed during inspection. We present a method which exploits additional information in neighbouring frames from video footage to reduce specularity from each frame. The technique first automatically determines frames which contain overlapping regions before the relationship that exists between them is exploited in order to suppress the effects of specular reflections. This results in an image that is free from specular highlights provided there is at least one frame present in the sequence where a given pixel is present in a diffuse form. The method is shown to work well on greyscale as well as colour images and effectively reduces specularity and significantly improves the quality of the stitched image, even in the presence of noise. While applied to the challenge of reducing specularity in inspection videos, the method improves upon the state-of-the-art in specularity removal, and, its applications are wider ranging as a general purpose pre-processing tool.
LanguageEnglish
Pages409-420
Number of pages12
JournalMachine Vision and Applications
Volume28
Issue number3
Early online date18 Feb 2017
DOIs
Publication statusPublished - 26 Apr 2017

Fingerprint

Inspection
Concrete construction
Pixels
Pipe
Color
Defects
Processing
Gases

Keywords

  • image projection
  • specular reflection removal
  • visual inspection
  • non-destructive evaluation

Cite this

@article{c021dad1090d4f8fa7540ac1f198c80f,
title = "Removal of specular reflections from image sequences using feature correspondences",
abstract = "The presence of specular highlights can hide underlying features of a scene within an image and can be problematic in many application scenarios. In particular, this poses a significant challenge for applications where image stitching is used to create a single static image of a scene from inspection footage of pipes, gas tubes, train tracks and concrete structures. Furthermore, they can hide small defects in the images causing them to be missed during inspection. We present a method which exploits additional information in neighbouring frames from video footage to reduce specularity from each frame. The technique first automatically determines frames which contain overlapping regions before the relationship that exists between them is exploited in order to suppress the effects of specular reflections. This results in an image that is free from specular highlights provided there is at least one frame present in the sequence where a given pixel is present in a diffuse form. The method is shown to work well on greyscale as well as colour images and effectively reduces specularity and significantly improves the quality of the stitched image, even in the presence of noise. While applied to the challenge of reducing specularity in inspection videos, the method improves upon the state-of-the-art in specularity removal, and, its applications are wider ranging as a general purpose pre-processing tool.",
keywords = "image projection, specular reflection removal, visual inspection, non-destructive evaluation",
author = "{M. Z. Abbas Shah}, Syed. and Stephen Marshall and Paul Murray",
note = "The final publication is available at Springer via http://dx.doi.org/10.1007/s00138-017-0826-6",
year = "2017",
month = "4",
day = "26",
doi = "10.1007/s00138-017-0826-6",
language = "English",
volume = "28",
pages = "409--420",
journal = "Machine Vision and Applications",
issn = "0932-8092",
number = "3",

}

Removal of specular reflections from image sequences using feature correspondences. / M. Z. Abbas Shah, Syed.; Marshall, Stephen; Murray, Paul.

In: Machine Vision and Applications, Vol. 28, No. 3, 26.04.2017, p. 409-420.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Removal of specular reflections from image sequences using feature correspondences

AU - M. Z. Abbas Shah, Syed.

AU - Marshall, Stephen

AU - Murray, Paul

N1 - The final publication is available at Springer via http://dx.doi.org/10.1007/s00138-017-0826-6

PY - 2017/4/26

Y1 - 2017/4/26

N2 - The presence of specular highlights can hide underlying features of a scene within an image and can be problematic in many application scenarios. In particular, this poses a significant challenge for applications where image stitching is used to create a single static image of a scene from inspection footage of pipes, gas tubes, train tracks and concrete structures. Furthermore, they can hide small defects in the images causing them to be missed during inspection. We present a method which exploits additional information in neighbouring frames from video footage to reduce specularity from each frame. The technique first automatically determines frames which contain overlapping regions before the relationship that exists between them is exploited in order to suppress the effects of specular reflections. This results in an image that is free from specular highlights provided there is at least one frame present in the sequence where a given pixel is present in a diffuse form. The method is shown to work well on greyscale as well as colour images and effectively reduces specularity and significantly improves the quality of the stitched image, even in the presence of noise. While applied to the challenge of reducing specularity in inspection videos, the method improves upon the state-of-the-art in specularity removal, and, its applications are wider ranging as a general purpose pre-processing tool.

AB - The presence of specular highlights can hide underlying features of a scene within an image and can be problematic in many application scenarios. In particular, this poses a significant challenge for applications where image stitching is used to create a single static image of a scene from inspection footage of pipes, gas tubes, train tracks and concrete structures. Furthermore, they can hide small defects in the images causing them to be missed during inspection. We present a method which exploits additional information in neighbouring frames from video footage to reduce specularity from each frame. The technique first automatically determines frames which contain overlapping regions before the relationship that exists between them is exploited in order to suppress the effects of specular reflections. This results in an image that is free from specular highlights provided there is at least one frame present in the sequence where a given pixel is present in a diffuse form. The method is shown to work well on greyscale as well as colour images and effectively reduces specularity and significantly improves the quality of the stitched image, even in the presence of noise. While applied to the challenge of reducing specularity in inspection videos, the method improves upon the state-of-the-art in specularity removal, and, its applications are wider ranging as a general purpose pre-processing tool.

KW - image projection

KW - specular reflection removal

KW - visual inspection

KW - non-destructive evaluation

UR - http://link.springer.com/journal/138

UR - https://link.springer.com/article/10.1007/s00138-017-0826-6

U2 - 10.1007/s00138-017-0826-6

DO - 10.1007/s00138-017-0826-6

M3 - Article

VL - 28

SP - 409

EP - 420

JO - Machine Vision and Applications

T2 - Machine Vision and Applications

JF - Machine Vision and Applications

SN - 0932-8092

IS - 3

ER -