Sciweavers

23 search results - page 2 / 5
» Limits of Learning-Based Superresolution Algorithms
Sort
View
ICIP
2005
IEEE
14 years 6 months ago
Non-parametric image super-resolution using multiple images
In this paper, we present a novel learning based framework for performing super-resolution using multiple images. We model the image as an undirected graphical model over image pa...
Mithun Das Gupta, ShyamSundar Rajaram, Nemanja Pet...
ICB
2007
Springer
207views Biometrics» more  ICB 2007»
13 years 8 months ago
Super-Resolved Faces for Improved Face Recognition from Surveillance Video
Characteristics of surveillance video generally include low resolution and poor quality due to environmental, storage and processing limitations. It is extremely difficult for comp...
Frank Lin, Clinton Fookes, Vinod Chandran, Sridha ...
ISCAS
2008
IEEE
169views Hardware» more  ISCAS 2008»
13 years 11 months ago
Sigma-delta learning for super-resolution independent component analysis
— Many source separation algorithms fail to deliver robust performance in presence of artifacts introduced by cross-channel redundancy, non-homogeneous mixing and highdimensional...
Amin Fazel, Shantanu Chakrabartty
ICIP
2008
IEEE
14 years 6 months ago
A block-based super-resolution for video sequences
An algorithm for video resolution enhancement is presented. The approach borrows from previous methods for still-image superresolution, introducing modifications better suited for...
Ryan S. Prendergast, Truong Q. Nguyen
ICASSP
2008
IEEE
13 years 11 months ago
Robust image registration with illumination, blur and noise variations for super-resolution
Super-resolution reconstruction algorithms assume the availability of exact registration and blur parameters. Inaccurate estimation of these parameters adversely affects the quali...
Himanshu Arora, Anoop M. Namboodiri, C. V. Jawahar