SAR Image Segmentation by Selected Principal Components and Kernel Graph Cuts Ensembles
Abstract
Graph cuts (GC) have become one of the most important methodologies in image segmentation. Recently, some researches tend to study GC and kernel mapping of the image pixels. However, most of the methods of existing kernel GC (KGC) image segmentation not only suffers from different types of noise, but also suffers from the settings of the regularizing parameter, which is used to balance the edge and region terms in the existing KGC. This paper is to investigate the image segmentation via principal component analysis and KGC ensemble. The principal components are selected by the estimated strength of introduced noise, which is calculated by the maximum statistics of variation coefficient. Besides, the regularization term of KGC is difficult to choose the appropriate scaling factor value for the regularization term, and it is always obtained by experience. Here, we aim to present KGC ensemble strategy to combine the segmenting results under different settings of scaling parameter. Furthermore, to achieve higher segmenting accuracy, the KGC is implemented in the projected lower dimensional subspace by selected principal components. Experiments on synthetic image, nature image, medical image and real SAR images demonstrate the advantages of the proposed algorithm over the existing KGC, two variants of fuzzy c-means not only in region consistence but also in the boundary localization.
