Shyju Wilson

Learn More
In this paper we propose and justify a methodology for the development of the control systems, or`cognitive a r c hitectures', of autonomous mobile robots. We argue that the design by hand of such control systems becomes prohibitively diicult as complexity increases. We discuss an alternative approach, involving artiicial evolution, where the basic building(More)
We have developed a methodology grounded in two beliefs: that autonomous agents need visual processing capabilities , and that the approach of hand-designing control architectures for autonomous agents is likely to be superseded by methods involving the artiicial evolution of comparable architectures. In this paper we present results which demonstrate that(More)
Classifying action videos became challenging problem in computer vision community. In this work, action videos are represented by dictionaries which are learned by online dictionary learning (ODL). Here, we have used two simple measures to classify action videos, reconstruction error and projection. Sparse approximation algorithm LASSO is used to(More)
The face, iris and finger print are among the most promising biometric authentication that can precisely identify and analysis a person as their unique textures can be quickly extracted during the recognition process. This biometric detection and authentication often deals with non-ideal scenarios such as blurred images, off-angles, reflections, expression(More)
Pervasive computing systems such as smart spaces typically combine multiple embedded and/or mobile sensing, computing and interaction devices. A variety of distributed computing approaches are used to integrate these devices to support coordinated applications. This paper describes how simple user descriptions of (primarily) physical aspects of such a(More)
  • 1