Title
Convolutional sparse representations as an image model for impulse noise restoration
Abstract
Standard sparse representations, applied independently to a set of overlapping image blocks, are a very effective approach to a wide variety of image reconstruction problems. Convolutional sparse representations, which provide a single-valued representation optimised over an entire image, provide an alternative form of sparse representation that has recently started to attract interest for image reconstruction problems. The present paper provides some insight into the suitability of the convolutional form for this type of application by comparing its performance as an image model with that of the standard model in an impulse noise restoration problem.
Year
DOI
Venue
2016
10.1109/IVMSPW.2016.7528229
2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP)
Keywords
Field
DocType
Sparse Representation,Convolutional Sparse Coding,Salt-and-Pepper Noise
Iterative reconstruction,Computer vision,Convolutional code,Pattern recognition,Feature detection (computer vision),Convolution,Sparse approximation,Artificial intelligence,Impulse noise,Image restoration,Mathematics,Encoding (memory)
Conference
ISBN
Citations 
PageRank 
978-1-5090-1930-4
2
0.38
References 
Authors
0
1
Name
Order
Citations
PageRank
Brendt Wohlberg168555.53