Noise-Robust Method for Image Segmentation

Abstract

Abstract. Segmentation of noisy images is one of the most challenging problems in image analysis and any improvement of segmentation methods can highly influence the performance of many image processing applications. In automated image segmentation, the fuzzy c-means (FCM) clustering has been widely used because of its ability to model uncertainty within the data, applicability to multi-modal data and fairly robust behaviour. However, the standard FCM algorithm does not consider any information about the spatial image context and is highly sensitive to noise and other imaging artefacts. Considering above mentioned problems, we developed a new FCM-based approach for the noise-robust fuzzy clustering and we present it in this paper. In this new iterative algorithm we incorporated both spatial and feature space information into the similarity measure and the membership function. We considered that spatial information depends on the relative location and features of the neighbouring pixels. The performance of the proposed algorithm is tested on synthetic image with different noise levels and real images. Experimental quantitative and qualitative segmentation results show that our method efficiently preserves the homogeneity of the regions and is more robust to noise than other FCM-based methods.

Automated Simulation Framework for Urban Wind Environments Based on Aerial Point Clouds and Deep Learning

“…Nevertheless, noises exist in the point clouds generated by oblique photography due to reasons such as occlusion, parallax, texture loss, and lighting conditions [73]. Many studies have lain their emphasis on the issue of data noise [74,75]. However, common noise filtering algorithms for point clouds, such as statistical outlier removal and radius outlier removal, significantly rely on parameter settings.…”

Application of the Maximum Flow–Minimum Cut Algorithm to Segmentation and Clustering of Materials Datasets

“…Consider the problem of segmenting a micrograph of a material containing multiple thermodynamic phases: A naïve approach for segmentation consists of identifying a threshold on the intensity which will classify the image pixels by phase. More often than not, this approach will fail due to insufficient contrast between the phases, uneven illumination of the sample, surface topology of the sample, noise in the image, etc (McInerney & Terzopoulos, 1999; Despotović et al, 2010; Zhu et al, 2013). Denoising, or some other form of cleanup, will oftentimes be applied to the data in order to remove some of these artifacts before or after segmentation; however, this approach can be resource intensive, is not easily automated, and may only be partially successful (Preethi & Narmadha, 2012; Soni et al, 2014).…”

Robust fuzzy c‐means clustering algorithm using non‐parametric Bayesian estimation in wavelet transform domain for noisy MR brain image segmentation

“…Despotovic et al [19] presented a new method based on the FCM clustering for segmenting noisy images. They integrated spatial neighbourhoods information of the image pixels into both the similarity measure and the membership function.…”