Implementation of Segmentation Scheme based on Wavelet Transform in Multi-Spectral Fluctuation Patterns

Authors

  • Melinda Melinda Electrical Department, Engineering Faculty, Universitas Indonesia, Campus Depok, 16424, Depok, Jawa Barat, Indonesia. Electrical Department, Engineering Faculty, University of Syiah Kuala, Banda Aceh, 23111, Aceh, Indonesia.
  • Agus Santoso Tamsir Electrical Department, Engineering Faculty, Universitas Indonesia, Campus Depok, 16424, Depok, Jawa Barat, Indonesia.
  • Dodi Sudiana Electrical Department, Engineering Faculty, Universitas Indonesia, Campus Depok, 16424, Depok, Jawa Barat, Indonesia.
  • Dadang Gunawan Electrical Department, Engineering Faculty, Universitas Indonesia, Campus Depok, 16424, Depok, Jawa Barat, Indonesia.
  • Muhammad Iqbal Electrical Department, Engineering Faculty, Universitas Indonesia, Campus Depok, 16424, Depok, Jawa Barat, Indonesia.

Keywords:

Segmentation, Fluctuation Pattern, Peak Of Amplitude

Abstract

Segmentation is one of signal processing methods that is fruitful to recognize some details of parts contained in a detail pattern before will be further processed. This study proposed a segmentation scheme, which is the input is based on the output of approximation of level two from wavelet transformation of 2D-DWT (Two Dimension Discrete Wavelet Transform). The segmentation scheme and algorithm process are implemented on the fluctuations patterns of HHF (High High-fluctuation) in multi spectral that previously are extracted. The fluctuation patterns of HHF are 2D (Dimensional) graphic that consist of matrix of the average value and standard deviation inside. The method that will be used is to apply the approach of segmentation scheme, which is suitable for treating HHF fluctuation pattern. Moreover, it also employs the approach to acquire the highest amplitude value and also to present the signals in the segments that have the top peak these fluctuations. In addition, there are some parameters that are very prominent in segmentation results to be analyzed, such as: the number of segments, the input frequency, spectral noise, the peak of amplitude value and VMR (variance to mean ratio). Furthermore, the analysis results of these parameters will be compared between the highest top three segments in the pattern fluctuation of HHF. Based on the results, it is noticeable to say that the segmentation scheme can be implemented for HHF pattern. Moreover, there are some segments that have the highest peak of amplitude values and also some parameters show quite striking phenomenon compare to other segments with the same parameters. In addition, the result of VMR is suitable with the statistical approach at VMR <1.  It can be said that the proposed segmentation approach can provide the illustration of the segment each of pattern fluctuations HHF clearly.

References

Y. Li, “Wavelet-based fuzzy multiphase image segmentation method ✩,” Pattern Recognit. Lett., vol. 53, pp. 1–8, 2015.

H. Azami, H. Hassanpour, J. Escudero, and S. Sanei, “An intelligent approach for variable size segmentation of non-stationary signals,” J. Adv. Res., vol. 6, no. 5, pp. 687–698, 2015.

M. Chain and M. Carlo, “Image Segmentation by Data-Driven,” IEEE Trans. PATTERN Anal. Mach. I, vol. 24, no. 5, pp. 657–673, 2002.

A. C. Fan, J. W. F. Iii, W. M. W. Iii, J. J. Levitt, and A. S. Willsky, “MCMC Curve Sampling for Image Segmentation,” MICCAI 2007, pp. 477–485, 2007.

H. Li, H. He, and Y. Wen, “Optik Dynamic particle swarm optimization and K-means clustering algorithm for image segmentation,” Opt. - Int. J. Light Electron Opt., vol. 126, no. 24, pp. 4817–4822, 2015.

Y. Yang, Y. Wang, and X. Xue, “Optik A novel spectral clustering method with superpixels for image segmentation,” Opt. - Int. J. Light Electron Opt., vol. 127, no. 1, pp. 161–167, 2016.

V. Grau, A. U. J. Mewes, M. Alcañiz, R. Kikinis, and S. K. Warfield, “Improved Watershed Transform for Medical Image Segmentation Using Prior Information,” IEEE Trans. Med. Imaging, vol. 23, no. 4, pp. 447–458, 2004.

Melinda, S.T.Agus, G. Dadang, S. Dodi, “Consistency Analysis of Mapping System of Noise Spectral Fluctuations in Multi-Frequency using Two-Dimension Discrete Wavelet Transform (2D-DWT),” in ASEA-UNINET 2016, 2016, pp. 48–62.

Y. Li and X. Feng, “A multiscale image segmentation method,” Pattern Recognit., vol. 52, pp. 332–345, 2016.

K. Fatima, “A Novel Architecture for the Computation of 2D-DWT and its Implementation on Virtex-II Pro FPGA,” in Computational Intelligence and Security, 2007, pp. 531–535.

H. Imtiaz and S. A. Fattah, “A Wavelet-domain Local Feature Selection Scheme for Face Recognition,” IEEE, vol. 11, pp. 448–451, 2011.

K. H. Ghazali, M. F. Mansor, M. M. Mustafa, and A. Hussain, “Feature Extraction Technique using Discrete Wavelet Transform for Image Classification,” in SCOReD, 2007, no. December, pp. 5–8.

S. G. C. S, “Image Compression and Denoising Effects using Wavelets,” IJNTEC, vol. 2, pp. 1–4, 2014.

A. Materka, “Discrete Wavelet Transform – Derived Features For Digital Image Texture Analysis,” in Signal and Electronic Systems, 2001, no. September, pp. 163–168.

S. Mallat, “A Wavelet Tour of Signal Processing,” A Wavelet Tour Signal Process., pp. 20–41, 1999.

Downloads

Published

2016-12-01

How to Cite

Melinda, M., Tamsir, A. S., Sudiana, D., Gunawan, D., & Iqbal, M. (2016). Implementation of Segmentation Scheme based on Wavelet Transform in Multi-Spectral Fluctuation Patterns. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 8(12), 47–52. Retrieved from https://jtec.utem.edu.my/jtec/article/view/1434