The Experts below are selected from a list of 521628 Experts worldwide ranked by ideXlab platform
Jianhong Shen - One of the best experts on this subject based on the ideXlab platform.
-
Bayesian Video Dejittering by the BV Image Model
Siam Journal on Applied Mathematics, 2004Co-Authors: Jianhong ShenAbstract:Line jittering, or random horizontal displacement in video Images, occurs when the synchronization signals are corrupted in video storage media, or by electromagnetic interference in wireless video transmission. The goal of intrinsic video dejittering is to recover the ideal video directly from the observed jittered and often noisy frames. The existing approaches in the literature are mostly based on local or semilocal filtering techniques and autoregressive Image Models and are complemented by various Image processing tools. In this paper, based on the statistical rationale of Bayesian inference, we propose the first variational dejittering Model based on the bounded variation (BV) Image Model, which is global, clean and self-contained, and intrinsically combines dejittering with denoising. The mathematical properties of the Model are studied based on the direct method of calculus of variations. We design one effective algorithm and present its computational implementation based on techniques from numeri...
-
Digital inpainting based on the Mumford{Shah{Euler Image Model
European Journal of Applied Mathematics, 2002Co-Authors: Selim Esedoglu, Jianhong ShenAbstract:Image inpainting is an Image restoration problem, in which Image Models play a critical role, as demonstrated by Chan, Kang & Shen's [12] recent inpainting schemes based on the bounded variation and the elastica [11] Image Models. In this paper, we propose two novel inpainting Models based on the Mumford–Shah Image Model [41], and its high order correction – the Mumford–Shah–Euler Image Model. We also present their efficient numerical realization based on the Γ -convergence approximations of Ambrosio & Tortorelli [2, 3] and De Giorgi [21].
-
Digital inpainting based on the Mumford-Shah-Euler Image Model
European Journal of Applied Mathematics, 2002Co-Authors: Selim Esedoglu, Jianhong ShenAbstract:Image inpainting is an Image restoration problem, in which Image Models play a critical role, as demonstrated by Chan, Kang & Shen's [12] recent inpainting schemes based on the bounded variation and the elastica [11] Image Models. In this paper, we propose two novel inpainting Models based on the Mumford–Shah Image Model [41], and its high order correction – the Mumford–Shah–Euler Image Model. We also present their efficient numerical realization based on the Γ -convergence approximations of Ambrosio & Tortorelli [2, 3] and De Giorgi [21].
-
A Good Image Model Eases Restoration
2002Co-Authors: Tony F. Chan, Jianhong ShenAbstract:Abstract : What we believe Images are determines how we take actions in Image and lowlevel vision analysis. In the Bayesian framework, it is known as the importance of a good Image prior Model. This paper intends to give a concise overview on the vision foundation, mathematical theory, computational algorithms, and various classical as well as unexpected new applications of the BV (bounded variation) Image Model, first introduced into Image processing by Rudin, Osher, and Fatemi in 1992 Physica D, 60:259-268.
-
A good Image Model eases restoration - on the contribution of Rudin-Osher-Fatmi's BV Image Model
2002Co-Authors: Tony F. Chan, Jianhong ShenAbstract:What we believe Images are determines how we take actions in Image and lowlevel vision analysis. In the Bayesian framework, it is known as the importance of a good Image prior Model. This paper intends to give a concise overview on the vision foundation, mathematical theory, computational algorithms, and various classical as well as unexpected new applications of the BV (bounded variation) Image Model, first introduced into Image processing by Rudin, Osher, and Fatemi in 1992 [Physica D, 60:259-268].
Matthias Bethge - One of the best experts on this subject based on the ideXlab platform.
-
NIPS - Generative Image Modeling using spatial LSTMs
2015Co-Authors: Lucas Theis, Matthias BethgeAbstract:Modeling the distribution of natural Images is challenging, partly because of strong statistical dependencies which can extend over hundreds of pixels. Recurrent neural networks have been successful in capturing long-range dependencies in a number of problems but only recently have found their way into generative Image Models. We here introduce a recurrent Image Model based on multidimensional long short-term memory units which are particularly suited for Image Modeling due to their spatial structure. Our Model scales to Images of arbitrary size and its likelihood is computationally tractable. We find that it outperforms the state of the art in quantitative comparisons on several Image datasets and produces promising results when used for texture synthesis and inpainting.
-
generative Image Modeling using spatial lstms
arXiv: Machine Learning, 2015Co-Authors: Lucas Theis, Matthias BethgeAbstract:Modeling the distribution of natural Images is challenging, partly because of strong statistical dependencies which can extend over hundreds of pixels. Recurrent neural networks have been successful in capturing long-range dependencies in a number of problems but only recently have found their way into generative Image Models. We here introduce a recurrent Image Model based on multi-dimensional long short-term memory units which are particularly suited for Image Modeling due to their spatial structure. Our Model scales to Images of arbitrary size and its likelihood is computationally tractable. We find that it outperforms the state of the art in quantitative comparisons on several Image datasets and produces promising results when used for texture synthesis and inpainting.
Joachim M Buhmann - One of the best experts on this subject based on the ideXlab platform.
-
weakly supervised semantic segmentation with a multi Image Model
International Conference on Computer Vision, 2011Co-Authors: Alexander Vezhnevets, Vittorio Ferrari, Joachim M BuhmannAbstract:We propose a novel method for weakly supervised semantic segmentation. Training Images are labeled only by the classes they contain, not by their location in the Image. On test Images instead, the method predicts a class label for every pixel. Our main innovation is a multi-Image Model (MIM) - a graphical Model for recovering the pixel labels of the training Images. The Model connects superpixels from all training Images in a data-driven fashion, based on their appearance similarity. For generalizing to new test Images we integrate them into MIM using a learned multiple kernel metric, instead of learning conventional classifiers on the recovered pixel labels. We also introduce an “objectness” potential, that helps separating objects (e.g. car, dog, human) from background classes (e.g. grass, sky, road). In experiments on the MSRC 21 dataset and the LabelMe subset of [18], our technique outperforms previous weakly supervised methods and achieves accuracy comparable with fully supervised methods.
K Sauer - One of the best experts on this subject based on the ideXlab platform.
-
a generalized gaussian Image Model for edge preserving map estimation
IEEE Transactions on Image Processing, 1993Co-Authors: Charles A. Bouman, K SauerAbstract:The authors present a Markov random field Model which allows realistic edge Modeling while providing stable maximum a posterior (MAP) solutions. The Model, referred to as a generalized Gaussian Markov random field (GGMRF), is named for its similarity to the generalized Gaussian distribution used in robust detection and estimation. The Model satisfies several desirable analytical and computational properties for map estimation, including continuous dependence of the estimate on the data, invariance of the character of solutions to scaling of data, and a solution which lies at the unique global minimum of the a posteriori log-likelihood function. The GGMRF is demonstrated to be useful for Image reconstruction in low-dosage transmission tomography. >
Charles A. Bouman - One of the best experts on this subject based on the ideXlab platform.
-
A multiscale stochastic Image Model for automated inspection
IEEE Transactions on Image Processing, 1995Co-Authors: Daniel R. Tretter, Charles A. Bouman, Khalid W. Khawaja, Anthony A. MaciejewskiAbstract:In this paper, we develop a novel multiscale stochastic Image Model to describe the appearance of a complex threedimensional object in a two-dimensional monochrome Image. This formal Image Model is used in conjunction with Bayesian estimation techniques to perform automated inspection. The Model is based on a stochastic tree structure in which each node is an important subassembly of the three-dimensional object. The data associated with each node or subassembly is Modeled in a wavelet domain. We use a fast multiscale search technique to compute the sequential MAP (SMAP) estimate of the unknown position, scale factor, and 2-D rotation for each subassembly. The search is carried out in a manner similar to a sequential likelihood ratio test, where the process advances in scale rather than time. The results of this search determine whether or not the object passes inspection. A similar search is used in conjunction with the EM algorithm to estimate the Model parameters for a given object from a set of training Images. The performance of the algorithm is demonstrated on two different real assemblies.
-
Stochastic Image Models for algorithm design
1994Co-Authors: Daniel R. Tretter, Charles A. BoumanAbstract:In this work two different stochastic Image Models are proposed for use in two different areas of Image processing. First, we develop both a theory and specific methods for performing optimal transform coding of multispectral and multilayer Images. The theory is based on the assumption that the Image may be Modeled as a set of jointly stationary Gaussian random processes. Although we do not assume the autocorrelation has a separable form, we show that the optimal transform for coding has a partially separable structure. Three different algorithms are shown to be asymptotically optimal under different data constraints. The proposed coding techniques are implemented using subband filtering methods, and the various algorithms are tested on multispectral Images to determine their relative performance characteristics. We also develop a novel multiscale stochastic Image Model to describe the appearance of a complex three-dimensional object in a two-dimensional monochrome Image. This formal Image Model is used in conjunction with Bayesian estimation techniques to perform automated inspection. The Model is based on a stochastic tree structure in which each node is an important subassembly of the three-dimensional object. The data associated with each node or subassembly is Modeled in a wavelet domain. We use a fast multiscale search technique to compute the sequential MAP (SMAP) estimate of the unknown position, scale factor, and 2-D rotation for each subassembly. The search is carried out in a manner similar to a sequential likelihood ratio test, where the process advances in scale rather than time. The results of this search determine whether or not the object passes inspection. A similar search is used in conjunction with the EM algorithm to estimate the Model parameters for a given object from a set of training Images. The performance of the algorithm is demonstrated on two different real assemblies.
-
a generalized gaussian Image Model for edge preserving map estimation
IEEE Transactions on Image Processing, 1993Co-Authors: Charles A. Bouman, K SauerAbstract:The authors present a Markov random field Model which allows realistic edge Modeling while providing stable maximum a posterior (MAP) solutions. The Model, referred to as a generalized Gaussian Markov random field (GGMRF), is named for its similarity to the generalized Gaussian distribution used in robust detection and estimation. The Model satisfies several desirable analytical and computational properties for map estimation, including continuous dependence of the estimate on the data, invariance of the character of solutions to scaling of data, and a solution which lies at the unique global minimum of the a posteriori log-likelihood function. The GGMRF is demonstrated to be useful for Image reconstruction in low-dosage transmission tomography. >
