Advanced search
1 file | 1.43 MB Add to list

Automated visual inspection algorithm for the reflection detection and removing in image sequences

Author
Organization
Project
Abstract
Specular reflections are undesirable phenomena that can impair overall perception and subsequent image analysis. In this paper, we propose a modern solution to this problem, based on the latest achievements in this field. The proposed method includes three main steps: image enhancement, detection of specular reflections, and reconstruction of damaged areas. To enhance and equalize the brightness characteristics of the image, we use the alpha-rooting method with an adaptive choice of the optimal parameter alpha. To detect specular reflections, we apply morphological filtering in the HSV color space. At the final stage, there is a reconstruction of damaged areas using adversarial neural networks. This combination makes it possible to quickly and effectively detect and remove specular reflections, which is confirmed by a series of experiments given by the experimental section of this work.
Keywords
Specular reflections, image enhancement, alpha-rooting, HSV color space, morphological filtering, adversarial neural network, image inpainting, ENHANCEMENT

Downloads

  • SPIEupd.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 1.43 MB

Citation

Please use this url to cite or link to this publication:

MLA
Sizyakin, Roman, et al. “Automated Visual Inspection Algorithm for the Reflection Detection and Removing in Image Sequences.” TWELFTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2019), edited by Wolfgang Osten et al., vol. 11433, Society of Photo-Optical Instrumentation Engineers (SPIE), 2020, doi:10.1117/12.2559362.
APA
Sizyakin, R., Voronin, V. V., Gapon, N., Nadykto, A., Pizurica, A., & Zelensky, A. (2020). Automated visual inspection algorithm for the reflection detection and removing in image sequences. In W. Osten, D. P. Nikolaev, & J. Zhou (Eds.), TWELFTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2019) (Vol. 11433). Amsterdam, Netherlands: Society of Photo-Optical Instrumentation Engineers (SPIE). https://doi.org/10.1117/12.2559362
Chicago author-date
Sizyakin, Roman, Viacheslav V. Voronin, Nikolay Gapon, Alexey Nadykto, Aleksandra Pizurica, and Alexander Zelensky. 2020. “Automated Visual Inspection Algorithm for the Reflection Detection and Removing in Image Sequences.” In TWELFTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2019), edited by Wolfgang Osten, Dmitry P. Nikolaev, and J. Zhou. Vol. 11433. Society of Photo-Optical Instrumentation Engineers (SPIE). https://doi.org/10.1117/12.2559362.
Chicago author-date (all authors)
Sizyakin, Roman, Viacheslav V. Voronin, Nikolay Gapon, Alexey Nadykto, Aleksandra Pizurica, and Alexander Zelensky. 2020. “Automated Visual Inspection Algorithm for the Reflection Detection and Removing in Image Sequences.” In TWELFTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2019), ed by. Wolfgang Osten, Dmitry P. Nikolaev, and J. Zhou. Vol. 11433. Society of Photo-Optical Instrumentation Engineers (SPIE). doi:10.1117/12.2559362.
Vancouver
1.
Sizyakin R, Voronin VV, Gapon N, Nadykto A, Pizurica A, Zelensky A. Automated visual inspection algorithm for the reflection detection and removing in image sequences. In: Osten W, Nikolaev DP, Zhou J, editors. TWELFTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2019). Society of Photo-Optical Instrumentation Engineers (SPIE); 2020.
IEEE
[1]
R. Sizyakin, V. V. Voronin, N. Gapon, A. Nadykto, A. Pizurica, and A. Zelensky, “Automated visual inspection algorithm for the reflection detection and removing in image sequences,” in TWELFTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2019), Amsterdam, Netherlands, 2020, vol. 11433.
@inproceedings{8647351,
  abstract     = {{Specular reflections are undesirable phenomena that can impair overall perception and subsequent image analysis. In this paper, we propose a modern solution to this problem, based on the latest achievements in this field. The proposed method includes three main steps: image enhancement, detection of specular reflections, and reconstruction of damaged areas. To enhance and equalize the brightness characteristics of the image, we use the alpha-rooting method with an adaptive choice of the optimal parameter alpha. To detect specular reflections, we apply morphological filtering in the HSV color space. At the final stage, there is a reconstruction of damaged areas using adversarial neural networks. This combination makes it possible to quickly and effectively detect and remove specular reflections, which is confirmed by a series of experiments given by the experimental section of this work.}},
  articleno    = {{114332B}},
  author       = {{Sizyakin, Roman and Voronin, Viacheslav V. and Gapon, Nikolay and Nadykto, Alexey and Pizurica, Aleksandra and Zelensky, Alexander}},
  booktitle    = {{TWELFTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2019)}},
  editor       = {{Osten, Wolfgang and Nikolaev, Dmitry P. and Zhou, J.}},
  isbn         = {{9781510636439}},
  issn         = {{0277-786X}},
  keywords     = {{Specular reflections,image enhancement,alpha-rooting,HSV color space,morphological filtering,adversarial neural network,image inpainting,ENHANCEMENT}},
  language     = {{eng}},
  location     = {{Amsterdam, Netherlands}},
  pages        = {{9}},
  publisher    = {{Society of Photo-Optical Instrumentation Engineers (SPIE)}},
  title        = {{Automated visual inspection algorithm for the reflection detection and removing in image sequences}},
  url          = {{http://dx.doi.org/10.1117/12.2559362}},
  volume       = {{11433}},
  year         = {{2020}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: