• Jul 16, 2019 News!Good News! All papers from Volume 9, Number 3 have been indexed by Scopus!   [Click]
  • Mar 27, 2019 News!Good News! All papers from Volume 9, Number 1 have been indexed by Scopus!   [Click]
  • Jul 08, 2019 News!Vol.9, No.4 has been published with online version.   [Click]
General Information
    • ISSN: 2010-3700 (Online)
    • Abbreviated Title: Int. J. Mach. Learn. Comput.
    • Frequency: Bimonthly
    • DOI: 10.18178/IJMLC
    • Editor-in-Chief: Dr. Lin Huang
    • Executive Editor:  Ms. Cherry L. Chen
    • Abstracing/Indexing: Scopus (since 2017), EI (INSPEC, IET), Google Scholar, Crossref, ProQuest, Electronic Journals Library.
    • E-mail: ijmlc@ejournal.net
Dr. Lin Huang
Metropolitan State University of Denver, USA
It's my honor to take on the position of editor in chief of IJMLC. We encourage authors to submit papers concerning any branch of machine learning and computing.

IJMLC 2017 Vol.7(5): 139-143 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2017.7.5.636

Smoothing Filters for Waveform Image Segmentation

Kedir Kamu Sirur, Ye Peng, and Zhang Qinchuan
Abstract—In this paper, we studied the impact of smoothing filters when applied to waveform image preprocessing for segmentation. To find out the characteristics of the output, we made an experiment on both real time and synthetic images. During our experiment, we have considered frequency-domain waveform images, time-domain waveform images, and ordinary test images. All the sample images are converted to gray level image and then smoothed with smoothing spline functions. We applied both global filter and localized filters. Finally, all the images are segmented using Intersecting Cortical Model (ICM) algorithm. The result of the experiment is evaluated using Peak Signal to Noise Ratio (PSNR), Mean Squared Error (MSE) and Visual Comparison methods. This research found out that we should be selective when we use smoothing filters on waveform images because of the unique structural behavior and high sensitivity of waveform images. The results proved that using global smoothing filters for waveform image preprocessing has a drastic negative effect and can change the pertinent signals. On the other hand, the use of localized smoothing filters resulted in sounding segmentation result from image processing point of view. This study also proved the increased performance of localized smoothing filters when applied to frequency-domain waveform images than time-domain waveform images. Thus we propose to avoid using global smoothing parameters for preprocessing of waveform images for segmentation and strongly recommend using localized smoothing filters.

Index Terms—Global parameter, local parameter, segmentation, smoothing, waveform image.

Kedir Kamu Sirur, Ye Peng, and Zhang Qinchuan are with the University of Electronic Science and Technology of China, Chengdu, Sichuan, P. R. China (e-mail: kedirkan@yahoo.com,{yepeng,zhangqc}@uestc.edu.cn).


Cite: Kedir Kamu Sirur, Ye Peng, and Zhang Qinchuan, "Smoothing Filters for Waveform Image Segmentation," International Journal of Machine Learning and Computing vol. 7, no. 5, pp. 139-143, 2017.

Copyright © 2008-2019. International Journal of Machine Learning and Computing. All rights reserved.
E-mail: ijmlc@ejournal.net