Iterative region based Otsu thresholding of bright-field microscopic images of activated sludge

Image processing and analysis is a potential alternative monitoring tool for biodegradation in activated sludge wastewater treatment process. Accuracy of image analysis based predictive models depends on the quality of the segmentation of the microbial aggregates in microscopic images of activated s...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES) pp. 533 - 538
Main Authors Khan, Muhammad Burhan, Nisar, Humaira, Aun, Ng Choon, Lo, Po Kim
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2016
Subjects
Accuracy
activated sludge
Histograms
image processing
Image segmentation
Iterative algorithms
Lighting
Measurement
Microscopy
Noise
Otsu thresholding
segmentation assessmen
Software algorithms
Thresholding (Imaging)
Online AccessGet full text
DOI10.1109/IECBES.2016.7843507

Cover

More Information
Summary:Image processing and analysis is a potential alternative monitoring tool for biodegradation in activated sludge wastewater treatment process. Accuracy of image analysis based predictive models depends on the quality of the segmentation of the microbial aggregates in microscopic images of activated sludge. The segmentation of the images is hindered by irregular illumination and properties of the microbial aggregates such as varying opaqueness and size. In this paper, an iterative region based Otsu thresholding is proposed for the bright field microscopic images of activated sludge. The suggested approach takes not only the statistics of grayscale intensities into account but also the regional distribution of the illumination noise. The proposed algorithm is compared with state-of-the-art Otsu, iterative Otsu and local Otsu segmentation techniques. The performance of the algorithms is assessed using accuracy, Rand index (RI) and variation of information (VI). The proposed algorithm exhibited better performance in terms of all the metrics with accuracy 0.9854, RI 0.9721 and VI 0.2141.
DOI:10.1109/IECBES.2016.7843507