[Show abstract][Hide abstract] ABSTRACT: Conventional statistical thresholding methods use class variance sum as criterions for threshold selection. These approaches
neglect specific characteristic of practical images and fail to obtain satisfactory results when segmenting some images with
similar statistical distributions in the object and background. To eliminate the limitation, a novel statistical criterion
is defined by utilizing standard deviations of two thresholded classes, and the optimal threshold is determined by optimizing
the criterion. The proposed method was compared with several classic thresholding counterparts on a variety of infrared images
as well as general real-world ones, and the experimental results demonstrate its superiority.
[Show abstract][Hide abstract] ABSTRACT: Classic statistical thresholding methods based on maximizing between-class variance and minimizing class variance fail to achieve satisfactory results when segmenting a kind of image, where variance discrepancy between the object and background classes is large. The reason is that they take only class variance sum of some form as criterions for threshold selection, but neglect discrepancy of the variances. In this paper, a novel criterion combining the above two factors is proposed to eliminate the described limitation for classic statistical approaches and improve segmentation performance. The proposed method determines the optimal threshold by minimizing the criterion. The method was compared with several classic thresholding methods on a variety of images including some NDT images and laser cladding images, and the experimental results show the effectiveness of the algorithm.
Full-text · Article · Dec 2010 · AEU - International Journal of Electronics and Communications