Journal of the Korean Society for Industrial and Applied Mathematics

Korean Society for Industrial and Applied Mathematics (한국산업응용수학회)
권호 표지
DOI QR코드

DOI QR Code

COUNTING OF FLOWERS BASED ON K-MEANS CLUSTERING AND WATERSHED SEGMENTATION

  • PAN ZHAO (DEPARTMENT OF MATHEMATICS, CHONNAM NATIONAL UNIVERSITY) ;
  • BYEONG-CHUN SHIN (DEPARTMENT OF MATHEMATICS, CHONNAM NATIONAL UNIVERSITY)
  • Received : 2023.03.30
  • Accepted : 2023.05.06
  • Published : 2023.06.25
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a hybrid algorithm combining K-means clustering and watershed algorithms for flower segmentation and counting. We use the K-means clustering algorithm to obtain the main colors in a complex background according to the cluster centers and then take a color space transformation to extract pixel values for the hue, saturation, and value of flower color. Next, we apply the threshold segmentation technique to segment flowers precisely and obtain the binary image of flowers. Based on this, we take the Euclidean distance transformation to obtain the distance map and apply it to find the local maxima of the connected components. Afterward, the proposed algorithm adaptively determines a minimum distance between each peak and apply it to label connected components using the watershed segmentation with eight-connectivity. On a dataset of 30 images, the test results reveal that the proposed method is more efficient and precise for the counting of overlapped flowers ignoring the degree of overlap, number of overlap, and relatively irregular shape.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. 2023R1A2C1006588).

References

  1. S. Jardim, J. Antonio, and C. Mora. ' Graphical image region extraction with k-means clustering and watershed, Journal of Imaging, 8(6) (2022), 163.
  2. J. MacQueen. Some methods for classification and analysis of multivariate observations, University of California Press, Proceedings of 5th Berkeley Symposium on Math., Stat., and Prob, CA 1965.
  3. X. Zheng, Q. Lei, R. Yao, Y. Gong, and Q. Yin. Image segmentation based on adaptive k-means algorithm, EURASIP Journal on Image and Video Processing, (2018), 1-10.
  4. M. Schier, C. Reinders, and B. Rosenhahn. Constrained mean shift clustering, SIAM, Proceedings of the 2022 SIAM International Conference on Data Mining (SDM). Virginia, US 2022.
  5. K. Fukunaga and L. Hostetler. The estimation of the gradient of a density function, with applications in pattern recognition, IEEE Transactions on information theory, 21(1) (1975), 32-40. https://doi.org/10.1109/TIT.1975.1055330
  6. M. A. Carreira-Perpinan. A review of mean-shift algorithms for clustering, arXiv preprint arXiv:1503.00687, 2015.
  7. M. A. Carreira-Perpinan. Acceleration strategies for gaussian mean-shift image segmentation, IEEE, Proceedings of 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06), NY 2006.
  8. X. Wang, B. Qian, and I. Davidson. On constrained spectral clustering and its applications, Data Mining and Knowledge Discovery, 28 (2014), 1-30. https://doi.org/10.1007/s10618-012-0291-9
  9. A. Kornilov, I. Safonov, and I. Yakimchuk. A review of watershed implementations for segmentation of volumetric images, Journal of Imaging, 8(5) (2022), 127.
  10. A. Kucharski and A. Fabijanska. ' Cnn-watershed: A watershed transform with predicted markers for corneal endothelium image segmentation, Biomedical Signal Processing and Control, 68 (2021), 102805.
  11. D. Khattab, H. M. Ebied, A. S. Hussein, and M. F. Tolba. Color image segmentation based on different color space models using automatic grabcut, The Scientific World Journal, 2014 (2014), 126025.
  12. B. Basavaprasad and R. S. Hegadi. Improved grabcut technique for segmentation of color image, Int. J. Comput. Appl, (2014).
  13. A. Ciobanu, M. Costin, and T. Barbu. Extraction of main colors from a color digital image, Proceedings of 10th International Multidisciplinary Scientific Geoconference SGEM 2010, Bulgaria 2010.
  14. P. Zhao and B.-C. Shin. Detection and counting of flowers based on digital images using computer vision and a concave point detection technique, Journal of Korean Society of Industrial and Applied Mathematics, 27(1) (2023), 37-55.
  15. M. Lalitha, M. Kiruthiga, and C. Loganathan. A survey on image segmentation through clustering algorithm, International Journal of Science and Research, 2(2) (2013), 348-358.
  16. A. Gulhane, P. L. Paikrao, and D. Chaudhari. A review of image data clustering techniques, International Journal of Soft Computing and Engineering, 2(1) (2012), 212-215.
  17. S. Naz, H. Majeed, and H. Irshad. Image segmentation using fuzzy clustering: A survey, IEEE, Proceedings of 2010 6th international conference on emerging technologies (ICET), Islamabad, Pakistan 2010.
  18. S. Patil, A. Naik, M. Sequeira, G. Naik, and J. Parab. An algorithm for pre-processing of areca nut for quality classification, Lecture Notes in Networks and Systems, Springer, Proceedings of Second International Conference on Image Processing and Capsule Networks: ICIPCN 2021, Bangkok, Thailand 2022.
  19. K. Hajdowska, S. Student, and D. Borys. Graph based method for cell segmentation and detection in live-cell fluorescence microscope imaging, Biomedical Signal Processing and Control, 71 (2022), 103071.
  20. P. Tejas and S. Padma. A hybrid segmentation technique for brain tumor detection in mri images, Lecture Notes in Networks and Systems, Springer, Proceedings of Second International Conference on Image Processing and Capsule Networks: ICIPCN 2021, Bangkok, Thailand 2022.
  21. O. Library. OpenCV: Open source computer vision library. https://opencv.org, 2000-2021.
  22. L. Vincent and P. Soille. Watersheds in digital spaces: an efficient algorithm based on immersion simulations, IEEE Transactions on Pattern Analysis & Machine Intelligence, 13(06) (1991), 583-598. https://doi.org/10.1109/34.87344
  23. O. Cuisenaire and B. Macq. Fast euclidean distance transformation by propagation using multiple neighborhoods, Computer vision and Image understanding, 76(2) (1999), 163-172. https://doi.org/10.1006/cviu.1999.0783
  24. R. Fabbri, L. D. F. Costa, J. C. Torelli, and O. M. Bruno. 2d euclidean distance transform algorithms: A comparative survey, ACM Computing Surveys (CSUR), 40(1) (2008), 1-44. https://doi.org/10.1145/1322432.1322434
  25. Z. Wand, Y. Liu, Z. Guan, Z. Zhang, and Z. Zhang. Watershed segmentation method for overlapped objects based on adaptive multiple euclidean distance transformation, Computer Knowledge and Technology, (003):018, 2022.
  26. F. Robert, P. Simon, W. Ashley, and W. Erik. Connected components labeling, https://homepages.inf.ed.ac.uk/rbf/HIPR2/label.htm, 2003.
  27. c. SciPy. scipy.ndimage.label. last edited on February 19, 2023 Version: 1.10.1. https://docs.scipy.org/doc/scipy/reference/generated/scipy.ndimage.label.html, 2023.
  28. J. R. Weaver. Centrosymmetric (cross-symmetric) matrices, their basic properties, eigenvalues, and eigenvectors, The American Mathematical Monthly, 92(10) (1985), 711-717. https://doi.org/10.1080/00029890.1985.11971719
  29. iStockphoto LP. istock by getty images, https://www.istockphoto.com/kr/search/search-by-asset?assetid=961872668&assettype=image, 2023.
  30. F. Wikimedia. Elbow method (clustering), last edited on 22 February 2023. https://en.wikipedia.org/wiki/Elbow_method_(clustering), 2023.
  31. S. J. Devaraj. Emerging paradigms in transform-based medical image compression for telemedicine environment, Telemedicine technologies, Elsevier, (2019), 15-29.