Current Science

Open Access Open Access  Restricted Access Subscription Access

Quantitative Analysis of Marker-Based Watershed Image Segmentation


Affiliations
1 Department of Electronics Engineering, Madras Institute of Technology, Anna University, Chennai 600 044, India
 

A methodology is proposed by combining the application of markers along with watershed transformation and thresholding for image segmentation. Use of the traditional watershed algorithm is widespread because of its advantage of being able to produce a complete division of the image. However, its drawbacks include over-segmentation and noise sensitivity. Therefore, the marker-based watershed segmentation is proposed here to overcome these effects. First, the original image is preprocessed by filtering techniques in order to smoothen it. Secondly, the foreground objects are marked. Then, the background markers are computed. Finally, the marked image is transformed through watershed transformation. The area is computed for the segmented objects in the image. It has been proved that this method reduces the error percentage.

Keywords

Gradient Magnitude, Image Segmentation, Markers, Morphology, Watershed.
User
Notifications
Font Size

  • Gonzalez, R. C., Digital Image Processing, Publishing House of Electronics Industry, Beijing, 1998, 2nd edn, pp. 460–505.

  • Roerdink, Jos, B. T. M. and Meijster, A., The watershed transform: definitions, algorithms and parallelization strategies. Fundamen. Inform., 2000, 41(1,2), 187–228.

  • Haralick, R. M. and Shapiro, L. G., Image segmentation techniques. Comp. Vis. Graph Image Process., 1985, 29(1), 100–132.

  • Benson, C. C., Lajish, V. L. and Kumar, R., Brain tumor extraction from MRI brain images using marker based watershed algorithm. In IEEE International Conference on Advances in Computing, Communications and Informatics, Kerala, India, 2015.

  • Digabel, H. and Lantuéjoul, C., Iterative algorithms. In Proc. Second European Symp. Quantitative Analysis of Microstructures in Material Science, Biology and Medicine, Germany, Riederer Verlag, Stuttgart, 1978, vol. 19, no. 7, pp. 85–99.

  • Beucher, S. and Meyer, F., The morphological approach to segmentation: the watershed transformation.In Optical Engineering, Marcel Dekker, New York, 1992, vol. 34, p. 433.

  • Beucher, S. and Lantuéjoul, C., Use of watersheds in contour detection, 1979.

  • Han, B., Watershed segmentation algorithm based on morphological gradient reconstruction. In Second International Conference on Information Science and Control Engineering, Shanghai, China, 2015, pp. 533–536.

  • Lin, Yung-Chieh, et al., Comparison between immersion-based and toboggan-based watershed image segmentation. IEEE Trans. Image Process., 2006, 15(3), 632–640.

  • Sun, Y. and He, Guo-Jin, Segmentation of high-resolution remote sensing image based on marker-based watershed algorithm. In IEE Fifth International Conference on Fuzzy Systems and Knowledge Discovery, Shandong, China, 2008, vol. 4.

  • Gaetano, R. et al., Marker-controlled watershed-based segmentation of multi resolution remote sensing images. IEEE Trans. Geosci. Remote Sensing, 2015, 53(6), 2987–3004.

  • Gao, H., Xue, P. and Lin, W., A new marker-based watershed algorithm. In Proceedings of the IEEE International Symposium on Circuits and Systems, 2004, vol. 2.

  • Qingli, Z. and Zhaoyang, Z., Open–close by reconstruction on CNNUM. Ninth IEEE International Workshop on Cellular Neural Networks and their Applications, 2005.

  • Sharma, J., Rai, J. K. and Tewari, R. P., A combined watershed segmentation approach using k-means clustering for mammograms. In Second IEEE International Conference on Signal Processing and Integrated Networks, 2015.

  • Zhou, H., Wu, J. and Zhang, J., Digital Image Processing: Part II, Bookboon, 2010.

  • Niraimathi, Mohideen Fatima, M. and Seenivasagam, V., A fast fuzzy-c means based marker controlled watershed segmentation of clustered nuclei. In IEEE International Conference on Computer, Communication and Electrical Technology, 2011.

  • Fan, G. et al., Adaptive marker-based watershed segmentation approach for T cell fluorescence images. In Proceedings of the IEEE International Conference on Machine Learning and Cybernetics, 2013, vol. 2.

  • Xu, L. and Lu, H., Automatic morphological measurement of the quantum dots based on marker-controlled watershed algorithm. IEEE Trans. Nanotechnol., 2013, 12(1), 51–56.

  • Pandey, S. and Singh, M. D., Study and implementation of morphology for image segmentation. Doctoral Dissertation, 2010.

  • Zhou, Y. and Ren, H., Segmentation method for rock particles image based on improved watershed algorithm. International Conference on Computer Science & Service System, 2012.

  • Shylaja, S. S. et al., Feature extraction using marker based watershed segmentation on the human face. In IEEE International Conference on Computer Communication and Informatics, 2012.

  • Maurer, C. R., Qi, R. and Vijay Raghavan, A linear time algorithm for computing exact Euclidean distance transforms of binary images in arbitrary dimensions. IEEE Trans. Pattern Anal. Mach. Intell., 2003, 25(2), 265–270.

  • Hlavac, V. and Sára, R. (eds), Computer Analysis of Images and Patterns: 6th International Conference, Proceedings, Czech Republic, Prague, 6–8 September 1995, vol. 970.

  • AlAzawee, Shaher, W., Abdel-Qader, I. and Abdel-Qader, J., Using morphological operations – erosion based algorithm for edge detection. In IEEE International Conference on Electro/Information Technology, 2015.

  • Ding, K. and Weng, G., Robust active contours for fast image segmentation. Electron. Lett., 2016, 52(20), 1687–1688.

  • Sindhuri, M. S. and Anusha, N., Text separation in document images through Otsu’s method. In IEEE International Conference on Wireless Communications, Signal Processing and Networking, 2016.

  • Image Coins.png, retrieved from http://people.sc.fsu.edu/~jburkardt/data/png/coins.png (July 2011).


Abstract Views: 298

PDF Views: 87




  • Quantitative Analysis of Marker-Based Watershed Image Segmentation

Abstract Views: 298  |  PDF Views: 87

Authors

S. Madhumitha
Department of Electronics Engineering, Madras Institute of Technology, Anna University, Chennai 600 044, India
M. Manikandan
Department of Electronics Engineering, Madras Institute of Technology, Anna University, Chennai 600 044, India

Abstract


A methodology is proposed by combining the application of markers along with watershed transformation and thresholding for image segmentation. Use of the traditional watershed algorithm is widespread because of its advantage of being able to produce a complete division of the image. However, its drawbacks include over-segmentation and noise sensitivity. Therefore, the marker-based watershed segmentation is proposed here to overcome these effects. First, the original image is preprocessed by filtering techniques in order to smoothen it. Secondly, the foreground objects are marked. Then, the background markers are computed. Finally, the marked image is transformed through watershed transformation. The area is computed for the segmented objects in the image. It has been proved that this method reduces the error percentage.

Keywords


Gradient Magnitude, Image Segmentation, Markers, Morphology, Watershed.

References





DOI: https://doi.org/10.18520/cs%2Fv114%2Fi05%2F1007-1013