We propose a new image registration criterion that uses segmented versions of the images to exploit both the geometric and photometric characteristics of the distinct regions they...
We propose a novel patch-based image representation that is useful because it (1) inherently detects regions with repetitive structure at multiple scales and (2) yields a paramete...
Lena Gorelick, Andrew Delong, Olga Veksler, Yuri B...
This paper reports the present results of a research on unsupervised Persian morpheme discovery. In this paper we present a method for discovering the morphemes of Persian languag...
Abstract. In this work, we present two active shape models for the segmentation of tubular objects. The first model is built using cylindrical parameterization and minimum descrip...
This paper studies image segmentation based on the minimum description length (MDL) functional combining spatial regularization with a penality for the number of distinct segments...