In this letter, we propose a clustering model that efficiently mitigates image and video under/over-segmentation by combining generalized Gaussian mixture modeling and feature sele...
Abstract. A novel approach to create a general vision system is presented. The proposed method is based on a visual grammar representation which is transformed to a Bayesian networ...
From time to time, state-of-the-art contrast enhancement algorithms face undesired drawbacks, like loss of tiny details, enhancement of image noise, occasional overenhancement, an...
Pattern recognition and computer vision tasks are computationally intensive, repetitive, and often exceed the capabilities of the CPU, leaving little time for higher level tasks. ...
— This paper presents work-in-progress towards a C++ source-to-source translator that automatically seeks parallelisable code fragments and replaces them with code for a graphics...
Jay L. T. Cornwall, Olav Beckmann, Paul H. J. Kell...