The objective of this paper is to study the existing methods for unsupervised object recognition and image categorization and propose a model that can learn directly from the outp...
Abstract—In this paper, we introduce a reconstruction framework that explicitly accounts for image geometry when defining the spatial interaction between pixels in the filterin...
: A new hardware structure for implementation of soft morphological filters is presented in this paper. This is based on the modification of the majority gate technique. A pipeline...
Antonios Gasteratos, Ioannis Andreadis, Phillipos ...
We present a new technique for the display of high-dynamic-range images, which reduces the contrast while preserving detail. It is based on a two-scale decomposition of the image ...
Abstract--Can images be decomposed into the sum of a geometric part and a textural part? In a theoretical breakthrough, [Y. Meyer, Oscillating Patterns in Image Processing and Nonl...
Antoni Buades, Triet M. Le, Jean-Michel Morel, Lum...