K-means clustering algorithm in image recognition tasks
DOI:
https://doi.org/10.32703/2617-9040-2019-34-2-3Keywords:
image, algorithm, clustering, simulation, segmentation, temperature, railroad socket.Abstract
The article is an overview of the scientific direction of graphic image recognition based on the k-means clustering algorithm. In particular, we have analyzed the clustering of data in digital image identification problems; we have described the operation principle of this algorithm with an illustration, where the number of selected clusters is equal to two and we presented a block diagram of the algorithm. We have proposed a scheme for implementing a machine vision system using this algorithm in the process of detecting overheated sockets on rail. We have performed color-based segmentation simulations over infrared images to detect high temperature sections in MATLAB. More specifically: two conditional images are taken, showing the railroad socket, one of which is normal and the other is overheated. The simulation results show that color-based segmentation allows accurate segmentation of thermal imaging. The application of this algorithm in the process of creating software for thermographic cameras for the purpose of recognizing temperature is effective, because this algorithm enables image compression, speeds up data processing, and enables the thermal performance of railroad socket to be monitored at high speeds.
References
Татьянкін В. М. Спосіб ідентифікації образів. // Шостий технологічний уклад: механізми та перспективи розвитку. 2015. С. 79-81. URL: https://cyberleninka.ru/article/v/sposob-identifikatsii-obrazov. (дата звернення 25.10.2019).
Селянкин В. В., Скороход С. В. Анализ и обработка изображений в задачах компьютерного зрения: учебное пособие. Таганрог: Изд-во ЮФУ, 2015. 82 с.
Яшина Е. С. Использование метода кластеризации в информационно-аналитической системе / Е. С. Яшина, М. А. Щербак // Радіоелектронні і комп’ютерні системи. 2016. № 2 (76). С. 62–69. URL: http://nbuv.gov.ua/UJRN/recs_2016_2_11. (дата звернення 25.10.2019).
Neelambike S. Color image segmentation by clustering // International journal of advanced research in computer science & technology. 2014. Vol. 2. № 1. Р. 95-97.
Aqil Burney S.M. K-means cluster analysis for image segmentation // International Journal of Computer Applications. 2014. Vol. 96. № 4. Р. 8.
Nameirakpam Dh. Image segmentation using k-means clustering algorithm and subtractive clustering algorithm. Eleventh international multi-conference on information processing-2015 (IMCIP-2015). India. Р. 764 – 771.
Прибор обнаружения неисправных (нагретых) аварийных букс (ПОНАБ). // Учебно-образовательный портал «Все лекции». URL: http://vse-lekcii.ru/zheleznodorozhnyj-transport/ats/ponab. (дата звернення 25.10.2019).
Karaman S., Pezzatini D., Bimbo A. A multi-camera image processing and visualization system for train safety assessment. // Multimedia Tools and Applications. 2018. Vol. 77. № 2. Р. 1583–1604.
Термографія. // Файловий архів студентів: Фізико-технічні основи рентгенології. URL: https://studfile.net/preview/1785100/page:5/. (дата звернення 25.10.2019).
Принципы получения термографического изображения. // Файловый архив студентов: Лекция 8 «Принципы получения термографического изображения». URL: https://studfile.net/preview/2716754/. (дата звернення 25.10.2019).
K-Means Clustering. // An Introduction to Data Science: Modeling. URL: http://www.saedsayad.com/clustering_kmeans.htm. (дата звернення 25.10.2019).
K-Means Clustering. // A Tutorial on Clustering Algorithms: K-means. URL: https://home.deib.polimi.it/matteucc/Clustering/tutorial_html/kmeans.html. (дата звернення 25.10.2019).
Madushan D. Introductions to K-means Clustering. URL: https://medium.com/@dilekamadushan/introduction-to-k-means-clustering-7c0ebc997e00. (дата звернення 25.10.2019).
Методы кластерного анализа. Итеративные методы. // Интуит: Национальный открытый университет (Курс лекций). URL: https://www.intuit.ru/studies/courses/6/6/lecture/184. (дата звернення 25.10.2019).
Wu Wenbin, Yue Wu and Jintao Li. The Hyper-spectral Image Compression Based on K-Means Clustering and Parallel Prediction Algorithm. // International Conference on Smart Materials, Intelligent Manufacturing and Automation (SMIMA 2018), section: Digital Signal and Image Processing. 2018. Vol. 173: MATEC Web of Conferences. P. 4.
Karri Tata Rao, Ch. Ramesh. Baseline JPEG Image Compression with K-Means Clustering Based Algorithm. // International Journal of Computer Science and Mobile Computing. Vol. 4. № 4. 2015. Р. 379-386.
Tichun Wang, Hongyang Zhang, Lei Tian. Research of Computer Desktop Image Compression Clustering Algorithm. // CHEMICAL ENGINEERING TRANSACTIONS. 2016. Vol. 51. P. 1-6.
Downloads
Published
How to Cite
Issue
Section
License
Copyright: This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
