THE COMPUTER SYSTEM OF SHADOW LOCATING AND REMOVAL IN DIGITAL IMAGES

Authors

  • М. Е. Serdiuk Oles Honchar Dnipropetrovsk National University, Ukraine
  • V. G. Berkut Oles Honchar Dnipropetrovsk National University, Ukraine

DOI:

https://doi.org/10.15588/1607-3274-2017-2-14

Keywords:

Shadow detection, shadow removal, image processing, Lab color space, segmentation, shadow model

Abstract

Context. Presence of shaded areas in digital images may cause problems in processes of objects recognition, tracking, classification. Thus shadows identification and removal are important pre-processing stages, which are used in many computer vision algorithms.

Objective. The work objective is to find effective methods for automatic shadow detection and removal and development of a software system that implements the appropriate image processing.

Method. In this paper we have discussed several approaches to the process of identifying and converting shaded areas, analyzed their applicability for different types of shadows. For shadow localization two methods are used: the method with the transition to the Lab color space and the method with preliminary removal of texture. For shadow removing four methods are used: additive method, method based on a mathematical model of shadows, method with the transition to the Lab-space, constant method. We have proposed some stages modifications to improve the practical results.

Results. Computer system with automatic detection and elimination of shadows, using the above methods, was developed. The choice of methods is carried out depending on the type of shaded areas. Some options of methods are available for configuration. The system was tested on series of images. We have analyzed quality and speed of the implemented methods. Image processing results by different methods are shown.

Conclusions. Implemented in the presented computer system methods of shadow locating and removing with the proposed modificationswork effectively in different types of images. Additional settings allow to improve the results in some difficult cases. The system can be used for image pre-processing in order to avoid errors in further work of the computer vision algorithms

Author Biographies

М. Е. Serdiuk, Oles Honchar Dnipropetrovsk National University

PhD, Associate Professor, Associate Professor of Computer Technologies Department

V. G. Berkut, Oles Honchar Dnipropetrovsk National University

Graduate student of Computer Technologies Department

References

Deb K., Suny A. H. Shadow Detection and Removal Based on YCbCr Color Space, Smart Computing Review, 2014, Vol. 4, No. 1, pp. 23–32.

Finlayson G. D., Hordley S. D., Drew M. S. Removing Shadows from Images, In: Proceedings of 7th European Conference on Computer Vision. Part IV, ECCV’02. London, UK, Springer-Verlag, 2002, pp. 823–836.

Fredembach C., Finlayson G. D., Fredembach C. Simple Shadow Removal, In: Proceedings of 18th International Conference on Pattern Recognition, ICPR’06. IEEE Computer Society, 2006, pp. 832–835.

Finlayson G. D., Hordley S. D., Lu C., Drew M. S. On the Removal of Shadows from Images, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, Vol. 28, No. 1, pp. 59–68.

Arbel E., Hel-Or H. Texture-Preserving Shadow Removal in Color Images Containing Curved Surfaces [Electronic resource]. Access mode: http://cs.haifa.ac.il/hagit/papers/CONF/ CVPR07_ArbelHelOr-shadowRemoval.pdf.

Murali S., Govindan V. K. Shadow Detection and Removal from a Single Image Using LAB Color Space, Cybernetics and Information Technologies, 2013, Vol. 13, No. 1, pp. 95–103.

Blajovici C., Kiss P. J., Bonus Z., Varga L. Image Shadow Removal in Mathematica [Electronic resource]. Access mode: http://mathematica.stackexchange.com/questions/7414/image-shadowremoval-in-mathematica.

Shadow detection and removal from a single image [Electronic resource]. Access mode: http://www.inf.u-szeged.hu/projectdirs/ s s i p2 0 1 1 / t eamF /Sha d owRemova l /Docume nt a t i on/ Shadow%20detection%20and%20removal%20from%20a%20single%20image.pdf

Suny A. H., Mithila N. H. A Shadow Detection and Removal from a Single Image Using LAB Color Space, IJCSI International Journal of Computer Science Issues, 2013, Vol. 10, No. 2, pp. 270–273.

Canny J. A Computational Approach to Edge Detection [Electronic resource]. Access mode: https://perso.limsi.fr/vezien/ PAPIERS_ACS/canny1986.pdf.

Downloads

How to Cite

Serdiuk М. Е., & Berkut, V. G. (2017). THE COMPUTER SYSTEM OF SHADOW LOCATING AND REMOVAL IN DIGITAL IMAGES. Radio Electronics, Computer Science, Control, (2), 127–133. https://doi.org/10.15588/1607-3274-2017-2-14

Issue

No. 2 (2017): Radio Electronics, Computer Science, Control

Section

Progressive information technologies

License

Copyright (c) 2017 М. Е. Serdiuk, V. G. Berkut

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Creative Commons Licensing Notifications in the Copyright Notices

The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.

The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.

The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License CC BY-SA that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

  • Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.