Inthispaper we formulatethe Radon transform asa wnvolution integral over the Euclidean motion group (SE(2)) and provideaminimummeansquare error(MMSE) stochastic deconvolution meth...
There has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks. Scaling such models to full-sized, high-dimensional images re...
Honglak Lee, Roger Grosse, Rajesh Ranganath, Andre...
We present a novel image classification technique for detecting multiple objects (called subobjects) in a single image. In addition to image classifiers, we apply spatial relati...
This paper presents a method for prototyping grasp-sensitive surfaces using optical fibers. In this system one end of a fiber bundle is attached to an image sensor. The other en...
— In this paper we present a novel methodology for detection and tracking of facial features like eyes, nose and mouth in image sequences. The proposed methodology is intended to...
Maria Pateraki, Haris Baltzakis, Polychronis Konda...