Improved workflow for unguided multiphase image segmentation. (September 2018)

• Record Type: Journal Article
• Authors: West, Brendan A.; Hodgdon, Taylor S.; Parno, Matthew D.; Song, Arnold J.
• Is Part Of: Computers & geosciences. Volume 118(2018)
• Page Start: 91
• Page End: 99
• Publication Date: 2018-09
• Subjects: Image segmentation -- Multiphase segmentation -- Local deconvolution -- Non-Gaussian mixture modeling -- Granular media; Environmental policy -- Periodicals; 550.5
• DOI: 10.1016/j.cageo.2018.05.013
• Languages: English
• ISSNs: 0098-3004

Abstract

Abstract: Quantitative image analysis often depends on accurate classification of pixels through a segmentation process. However, imaging artifacts such as the partial volume effect and sensor noise complicate the classification process. These effects increase the pixel intensity variance of each constituent class, causing intensity values of one class to overlap with another. This increased variance makes threshold based segmentation methods insufficient due to ambiguous overlap regions in the pixel intensity distributions. The class ambiguity becomes even more complex for systems with more than two constituents, such as unsaturated moist granular media. In this paper, we propose an image processing workflow that improves segmentation accuracy for multiphase systems. First, the ambiguous transition regions between classes are identified and removed, which allows for global thresholding of single-class regions. Then the transition regions are classified using a distance function, and finally both segmentations are combined into one classified image. This workflow includes three methodologies for identifying transition pixels and we demonstrate on a variety of synthetic images that these approaches are able to accurately separate the ambiguous transition pixels from the single-class regions. One of these methods does not require any parameter tuning and is entirely unguided, whereas the other two require manual threshold specifications and are thus user-guided. For situations with typical amounts of image noise, misclassification errors and area differences calculated between each class of the synthetic images and the resultant segmented images range from 0.69 to 1.48% and 0.01 to 0.74%, respectively, showing the segmentation accuracy of this approach. We demonstrate that we are able to accurately segment x-ray microtomography images of moist granular media using these computationally efficient methodologies. Highlights: An unguided method for segmenting images of many constituent phases is proposed. Single-phase regions and complicated transition regions are segmented separately. Transition pixels are segmented using a local deconvolution method. Single-phase pixels are segmented using a Gaussian mixture model. The method performs well compared to user-guided segmentation methods.