A Review on Global Thresholding Methods for Image Binarization

Öz

Thresholding is one of the most essential issues in image processing. Although this technique is commonly used for segmentation of regions with different homogeneity in grayscale images, and it is also preferred for segmentation of colored images. In this study, 14 different algorithms capable of global thresholding on gray-scale images were categorized and examined in detail as cluster-based, entropy-based, shape-based and feature similarity-based. To test the performance of the algorithms, a dataset consisting of 15 different images was prepared. For these images, the threshold value was determined manually by four experts and reference binary images were obtained by calculating mean value. Accordingly, the binary images produced by each algorithm were examined with the similarity rates to the reference images using the Jaccard Index method. In experimental studies, it was seen that the highest score according to the average similarity ratio obtained belongs to the IsoData and Otsu algorithms with approximately 95%.

Anahtar Kelimeler

• Image processing
• Global thresholding
• Binarization

Görüntü İkileştirme için Global Eşikleme Yöntemleri Üzerine Bir İnceleme

Öz

Görüntü işlemede en temel konulardan biri eşikleme yöntemidir. Bu yöntem, yaygın olarak gri tonlamalı görüntülerdeki farklı homojenliğe sahip bölgelerin bölütlenmesinde kullanılmakla birlikte renkli görüntülerin bölütlenmesi için de tercih edilir. Bu çalışmada, gri ölçekli görüntüler üzerinde global eşikleme yapabilen 14 farklı algoritma; kümeleme tabanlı, entropi tabanlı, şekil tabanlı ve öznitelik benzerliğine dayalı olmak üzere kategorize edilmiş ve detaylı olarak incelenmiştir. Algoritmaların performansını test etmek için 15 farklı görüntüden oluşan bir veri seti hazırlanmıştır. Bu görüntüler için dört uzman tarafından el yordamıyla eşik değeri belirlenmiş ve ortalama değeri alınarak referans ikili görüntüler elde edilmiştir. Buna göre her bir algoritmanın ürettiği ikili görüntüler, Jaccard Index yöntemiyle referans görüntülere olan benzerlik oranları incelenmiştir. Deneysel çalışmalarda, elde edilen benzerlik oranı ortalamasına göre en yüksek skor yaklaşık %95 ile IsoData ve Otsu algoritmalarına ait olduğu görülmüştür.

Anahtar Kelimeler

• Görüntü işleme
• Global eşikleme
• İkileştirme

Kaynakça

1. [1] Kotte, S., Rajesh Kumar, P., & Injeti, S. K., “An efficient approach for optimal multilevel thresholding selection for gray scale images based on improved differential search algorithm”, Ain Shams Engineering Journal, vol. 9, no. 4, pp. 1043-1067, 2018.
2. [2] Wang, Z., Wang, E., & Zhu, Y., “Image segmentation evaluation: a survey of methods”, Artificial Intelligence Review., 2020.
3. [3] Ramola, A., Shakya, A.K., & Pham, D.V., “Study of statistical methods for texture analysis and their modern evolutions”, Engineering Reports, vol. 2, no. 4, pp. 1-24, 2020.
4. [4] Aqeel, E. F., “The Use of Threshold Technique in image segmentation”, Journal of the College of Basic Education, vol. 21, no. 89, pp. 1-12, 2015.
5. [5] Zaitoun, N.M., & Aqel, M.J., “Survey on Image Segmentation Techniques”, Procedia Computer Science, vol. 65, pp. 797-806, 2015.
6. [6] Singh, T.R., Roy, S., Singh, O.I., Sinam, T., & Singh, Kh.M., “A New Local Adaptive Thresholding Technique in Binarization”, International Journal of Computer Science Issues, vol. 8, no. 2, pp.271-277, 2011.
7. [7] Ceylan, R., & Koyuncu, H., “ScPSO-Based Multithresholding Modalities for Suspicious Region Detection on Mammograms”, Soft Computing Based Medical Image Analysis, Academic Press, pp. 109-135, 2018.
8. [8] Rosin, P., “Thresholding for change detection”. Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271), pp. 274-279, 1998.

9. [9] Ekielski, A., “An algorithm for determination of threshold value in extruded products by the method of maximum increments: modification of Otsu method”, Annals of Warsaw University of Life Sciences-SGGW, Agriculture no. 62, pp. 71–79, (2013).
10. [10] Sezgin, M. & Sankur, B., “Survey over Image Thresholding Techniques and Quantitative Performance Evaluation”, Journal of Electronic Imaging, vol. 13, no. 1, pp. 146-165, 2004.
11. [11] Otsu, N., “A threshold selection method from gray-level histograms”, IEEE Trans. Sys., Man., Cyber, vol. 9, pp. 62-66, 1979.
12. [12] Doyle, W., “Operation useful for similarity-invariant pattern recognition”, Journal of the Association for Computing Machinery vol. 9, pp. 259-267, 1962.
13. [13] Kittler, J., Illingworth, J. and Foglein, J., “Threshold selection based in a simple image statistic”, Computer Vision, Graphics and Image Processing, vol. 30, pp. 125-147, 1985.
14. [14] Ridler, T. W. & Calvard, S., “Picture thresholding using an iterative selection method”, IEEE Transactions on Systems, Man and Cybernetics, vol. 8, pp. 630-632, 1978.
15. [15] Glasbey, C. A., “An analysis of histogram-based thresholding algorithms”, CVGIP: Graphical Models and Image Processing, vol. 55, pp. 532-537, 1993.
16. [16] Kapur, J. N., Sahoo, P. K. & Wong, A. C. K., “A New Method for Gray-Level Picture Thresholding Using the Entropy of the Histogram”, Graphical Models and Image Processing, vol. 29, no. 3, pp. 273-285, 1985.
17. [17] Sahoo, P., Wilkins, C. & Yeager, J., “Threshold selection using Renyi's entropy”, Pattern Recognition, vol. 30, no. 1, pp. 71–84, 1997.
18. [18] Li, C. H. & Lee, C. K., “Minimum Cross Entropy Thresholding”, Pattern Recognition, vol. 26, no. 4, pp. 617-625, 1993.
19. [19] Li, C. H. & Tam, P. K. S., “An Iterative Algorithm for Minimum Cross Entropy Thresholding”, Pattern Recognition Letters, vol. 18, no.8, pp. 771-776, 1998.
20. [20] Shanbhag, Abhijit G., “Utilization of information measure as a means of image thresholding”, Graph. Models Image Process. (Academic Press, Inc.), vol. 56, no. 5, pp. 414-419, 1994.
21. [21] Yen J. C., Chang F. J., Chang S., “A New Criterion for Automatic Multilevel Thresholding”, IEEE Trans. on Image Processing, vol. 4, no. 3, pp. 370-378, 1995.
22. [22] Zack, G. W., Rogers, W. E., Latt, S. A., “Automatic measurement of sister chromatid exchange frequency”, J. Histochem. Cytochem, vol. 25, no. 7, pp. 741–53, 1977.
23. [23] Prewitt, J. M. S. & Mendelsohn, M. L., “The analysis of cell images”, Annals of the New York Academy of Sciences, vol. 128, pp. 1035-1053, 1966.
24. [24] Tsai, W., “Moment-preserving thresholding: a new approach”, Computer Vision, Graphics, and Image Processing, vol. 29, pp. 377-393, 1985.
25. [25] Huang, L-K. & Wang, M-J. J., “Image thresholding by minimizing the measure of fuzziness”, Pattern Recognition, vol. 28, no. 1, pp. 41-51, 1995.
26. [26] Stelios, K., Michail, K., & Vassilios, C., “An Empirical Method for Threshold Selection”, International Journal of Signal Processing, Image Processing and Pattern Recognition, vol. 5, no. 2, pp. 101-114, 2012.