Image Enhancement Sputum Containing Mycobacterium Tuberculosis Using A Spatial Domain Filter

9th Annual Basic Science International Conference 2019

自然科学（总论）

Rachmad, Aeri^1^2 ; Chamidah, Nur^3 ; Rulaningtyas, Riries^4

Doktoral Stud. at Faculty of Sciences and Technology, Airlangga University, Surabaya, Indonesia^1

Departemen of Informatics, Faculty of Engineering, University of Trunojoyo, Madura, Bangkalan, Indonesia^2

Department of Mathematics, Faculty of Sciences and Technology, Airlangga University, Surabaya, Indonesia^3

Department of Physics, Faculty of Sciences and Technology, Airlangga University, Surabaya, Indonesia^4

关键词: Adaptive noise removals;    Bilateral filtering;    Computational time;    Filtering technique;    Means square errors;    Mycobacterium tuberculosis;    Peak signal to noise ratio;    Spatial domain filter;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/546/5/052061/pdf
DOI  :  10.1088/1757-899X/546/5/052061

学科分类：自然科学（综合）

来源: IOP

【 摘 要 】

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.