Abstract
Image enhancement sputum is needed to identify bacteria mycobacterium tuberculosis (TB). The number of TB bacteria in sputum images determines the severity of tuberculosis sufferers. In this paper, we study image enhancement sputum techniques by using spatial domain filter-based methods such as median filtering, Gaussian filtering, adaptive noise-removal filtering and bilateral filtering. These filtering techniques are used to overcome the problems when taking sputum images such as adjusting the focus of the lens, lighting and dirt that stick to the lens and on the slide glass. The obtained results for 100 data sputum images from this study are average means square error (MSE) of median filtering, Gaussian filtering, adaptive noise-removal filtering and bilateral filtering, i.e., 30.68, 17.10, 18.92 and 26.28, respectively. Also, average peak signal-to-noise ratio (PSNR) of them are 33.70 dB, 35.91 dB, 35.59 dB and 34.01 dB, respectively. The avarage computational time are 0.09 sec, 0.18 sec, 0.38 sec and 134 sec respectively.
Export citation and abstract BibTeX RIS
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.