Segmentation of activated sludge flocs with modeling of illumination noise

Fault diagnosis of activated sludge wastewater treatment plant for abnormal operation can be done using image processing and analysis of microscopic images of samples collected from aeration tank of the plant. In this paper, a novel illumination compensated segmentation technique is proposed for bright field microscopic images of the activated sludge wastewater samples. The illumination noise is modeled as Gaussian distribution and used with global Otsu thresholding. The performance of the algorithm is assessed using accuracy and Rand index. The segmentation is assessed using gold approximations of ground truth images, which were prepared manually. The proposed algorithm is compared with the local adaptive algorithms of Sauvola and Bradley. The performance metrics showed better performance of the proposed algorithm.