Many volume filtering operations used for image enhancement, data processing or feature detection can be written in terms of threedimensional convolutions. It is not possible to y...
Restricted Boltzmann Machines (RBM) are well-studied generative models. For image data, however, standard RBMs are suboptimal, since they do not exploit the local nature of image ...
At the Human Computer Interaction Lab (HCILab) at UNC Charlotte, we investigate novel ways for people to interact with computers, and through computers with their environments. Ou...
Color and texture have been widely used in image segmentation; however, their performance is often hindered by scene ambiguities, overlapping objects, or missing parts. In this pa...
We propose a new multiple description method for wavelet transform coded images. The partitioning of the coefficients at the encoder is combined with concealment at the decoder to...
A. C. Ashwin, K. R. Ramakrishnan, S. H. Srinivasan