RESEARCH OF IMAGE SEGMENTATION METHODS FOR THEIR UNIFICATION

Authors

  • V.V. HRYTSYK

DOI:

https://doi.org/10.32782/KNTU2618-0340/2020.3.2-1.8

Keywords:

pattern recognition, image segmentation, computer vision

Abstract

The paper presents the author's research in the direction of reviewing effective methods of segmentation that can be used in the educational process today. The basic solutions and their mathematical substantiation are analyzed in the work. The main limitations of application and problem areas of application are shown. The paper describes the basic principles of threshold determination. Threshold methods are one of the easiest to implement and most widely used methods of image segmentation. The purpose of the threshold is to divide the image into regions with specified characteristics and delete all other regions that are considered insignificant. The material presented in this paper provides a basic understanding of the different strategies for selecting thresholds. The main goal of this paper is review of image segmentation methods. The necessity of constructing a mathematical model arises immediately when using a computer for image processing. By evaluating the "eye" affiliation of a pixel to a particular segment, we do not think about how it is done but for computer we need write algorithm. If the task is some adaptation, we need to have written all possibility conditions. Instructing this computer, we have to teach him to perform similar actions, that is, to put in it the corresponding data and algorithms. The paper investigates the methods of segmentation that are carried out primarily in order to reduce the information redundancy of the image for specific time conditions, leaving it only the information that is needed to solve a particular task at a specific time point. In the binary image, the parts that are of interest to us (for example, the outlines of the displayed objects) must be preserved and insignificant features (background) are excluded. The main idea is form the basis for teaching math in the system of perception. In particular, the computer should feel and understand the dynamics of the real world. Therefore, the author investigates the models and means of synthesizing the methods of perception of data of the visual spectrum, arriving in real time. Global threshold method, multilevel threshold method, semithreshold method, variable threshold method are studied in the paper. Mathematical base is studies and presented in the article. Mathematic of image processing is integrated in the end of every part.

References

Hrytsyk V., Grondzal A., Bilenkyj A. Augmented Reality for People with Disabilities. Proceedings of the International Conference on Computer Sciences and Information Technologies, CSIT’2015 (Lviv, September 14–17, 2015). Lviv: Polytechnic National University, 2015. P. 188–191.

Audio-Visual Answer to Modern Computing. Research*eu Results Supplement. 2010. № 26. P. 31−32.

Мічо Кайку. Фізика майбутнього. Переклала з англ. Анжела Кам’янець. Львів: Літопис, 2013. 432 с.

Software: Running Commentary for Smarter Surveillance? Research*eu Results Supplement. 2010. № 24. P. 29.

Schwab K. The Fourth Industrial Revolution: What it Means, How to Respond. World Economic Forum. URL: https://www.weforum.org/agenda/2016/01/the-fourthindustrial-revolution-what-it-means-and-how-to-respond

Шваб K. Четверта промислова революція: як до неї готуватися (переклад). URL: http://nubip.edu.ua/node/23076

Kagermann H., Lukas W.-D., Wahlster W.0 Industrie 4.0: Mit dem Internet der Dinge auf dem Weg zur 4. industriellen Revolution (нім.). VDI nachrichten. 2011, April 1, №13. URL: http://www.vdi-nachrichten.com/Technik-Gesellschaft/Industrie-40-MitInternet-Dinge-Weg-4industriellen-Revolution;

Шмідт Ф., Бутирський З. Ганноверський ярмарок: Інтернет зливається з заводом. Deutsche Welle. 2013. URL: http://www.dw.com/uk/ганноверський-ярмарокінтернет-зливається-з-заводом/a-16728837

Hermann M., Pentek T., Otto B. Design Principles for Industrie 4.0 Scenarios: A Literature Review. URL: http://www.snom.mb.tu-dortmund.de/cms/de/forschung/ Arbeitsberichte/Design-Principles-for-Industrie-4_0-Scenarios.pdf

Business Insider. URL: http://www.businessinsider.com/cyborgs-are-the-future-offinancial-advice-2017-2

Stuart J. Russell and Peter Norvig. Artificial Intelligence a Modern Approach. New Jersey: Prentice-Hall, Inc., 1995. 950 p.

Rosenfeld A., Kak A. Digital Picture processing. 2nd ed. New York: Academic Press,1982. 476 c.

Otsu N. A Threshold Selection Method from Gray-Level Histograms. Proceedings of the IEEE Transactions on Systems, Man, and Cybernetics. 1979. Vol. SMC-9. P. 62–66.

Sahoo P. K., Soltani S., Wong A. C., Chen Y. C. A Survey of Thresholding Techniques.Computer Vision, Graphics and Image Processing. 1988. Vol. 41. P. 233–260.

Ritter Gerhard X., Wilson Joseph N. Handbook of Computer Vision Algorithms in Image Algebra. 2nd Ed. Boca Raton, London, NewYork,Washington: CRC press, 2000. 448 p.

Korzynska A., Roszkowiak L., Lopez C., Bosch R., Witkowski L., Lejeune M. Validation of Various Adaptive Threshold Methods of Segmentation Applied to Follicular Lymphoma Digital Images Stained with 3,3’-Diaminobenzidine&Haematoxylin. Diagnostic Pathology. 2013. Issue 8. Article number 48. DOI: 10.1186/1746-1596-8-48

Sauvola J. Pietikainen M. Adaptive document image binarization. Pattern Recognition. 2000, 33, 225–236. DOI: 10.1016/S0031-3203(99)00055-2.

Hrytsyk V. V., Dunas A. Ya. Doslidzhennia metodiv rozpiznavannia obraziv dlia system kompiuternoho zoru robotiv maibutnoho. Visnyk KhNTU. 2017. № 3. Ч. 1, С. 297–301.

Published

2023-09-11