DocumentCode :
50281
Title :
Adaptive Image Resizing Based on Continuous-Domain Stochastic Modeling
Author :
Kirshner, Hagai ; Bourquard, Alex ; Ward, John Paul ; Porat, Moshe ; Unser, Michael
Author_Institution :
Biomed. Imaging Group, Ecole Polytech. Fed. de Lausanne, Lausanne, Switzerland
Volume :
23
Issue :
1
fYear :
2014
fDate :
Jan. 2014
Firstpage :
413
Lastpage :
423
Abstract :
We introduce an adaptive continuous-domain modeling approach to texture and natural images. The continuous-domain image is assumed to be a smooth function, and we embed it in a parameterized Sobolev space. We point out a link between Sobolev spaces and stochastic auto-regressive models, and exploit it for optimally choosing Sobolev parameters from available pixel values. To this aim, we use exact continuous-to-discrete mapping of the auto-regressive model that is based on symmetric exponential splines. The mapping is computationally efficient, and we exploit it for maximizing an approximated Gaussian likelihood function. We account for non-Gaussian Lévy-type processes by deriving a more robust estimator that is based on the sample auto-correlation sequence. Both estimators use multiple initialization values for overcoming the local minima structure of the fitting criteria. Experimental image resizing results indicate that the auto-correlation criterion can cope better with non-Gaussian processes and model mismatch. Our work demonstrates the importance of the auto-correlation function in adaptive image interpolation and image modeling tasks, and we believe it is instrumental in other image processing tasks as well.
Keywords :
autoregressive processes; correlation methods; image texture; interpolation; Sobolev parameters; adaptive image interpolation; adaptive image resizing; approximated Gaussian likelihood function; auto-correlation criterion; continuous-domain image; continuous-domain stochastic modeling; continuous-to-discrete mapping; fitting criteria; image modeling tasks; image processing tasks; local minima structure; model mismatch; natural images; nonGaussian Levy-type processes; nonGaussian processes; parameterized Sobolev space; pixel values; sample auto-correlation sequence; smooth function; stochastic auto-regressive models; symmetric exponential splines; Adaptation models; Computational modeling; Interpolation; Kernel; Splines (mathematics); Stochastic processes; Technological innovation; Auto-regressive parameter estimation; adaptive interpolation; exponential splines;
fLanguage :
English
Journal_Title :
Image Processing, IEEE Transactions on
Publisher :
ieee
ISSN :
1057-7149
Type :
jour
DOI :
10.1109/TIP.2013.2285597
Filename :
6632888
Link To Document :
بازگشت