High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...
Using different algorithms to segment different images is a quite straightforward strategy for automated image segmentation. But the difficulty of the optimal algorithm selection ...
We propose an unsupervised method for evaluating image segmentation. Common methods are typically based on evaluating smoothness within segments and contrast between them, and the...
This paper presents a method of overlapping/aggregating nuclei cells segmentation. This method is based on the watershed segmentation algorithm, but the specificity of this work i...
Computer users with visual impairment cannot access the rich graphical contents in print or digital media unless relying on visual-to-tactile conversion, which is done primarily b...