Results 11  20
of
42
Texture Classification Using Sparse Representations by Learned Compound Dictionaries
"... Abstract: A novel method for classification of texture images through sparse representation of image blocks is presented. The method enables us to classify multitexture images by using one single learned compound dictionary. Promising results are presented for two twotexture images and one fivetex ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Abstract: A novel method for classification of texture images through sparse representation of image blocks is presented. The method enables us to classify multitexture images by using one single learned compound dictionary. Promising results are presented for two twotexture images and one fivetexture image. Comparisons with other known classification methods show that the classification performance of our method is good. The processing time for texture classification using our method is seen to be shorter than using the FTCM method, in which one dictionary is learned for each class. 1
Fast Matching Pursuit Video Coding by Combining Dictionary Approximation and Atom Extraction
"... Abstract—In this paper, we propose a systematic approach that approximates a target dictionary to reduce the complexity of a matching pursuit encoder. We combine calculation of the inner products and maximum atom extraction of a matching pursuit video coding scheme based on eigendictionary approxima ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Abstract—In this paper, we propose a systematic approach that approximates a target dictionary to reduce the complexity of a matching pursuit encoder. We combine calculation of the inner products and maximum atom extraction of a matching pursuit video coding scheme based on eigendictionary approximation and treebased vector quantization. The approach makes the codec design and optimization cleaner and more systematic than previous dictionary approximation methods. We vary the quality of approximation to demonstrate the tradeoff between computational complexity and coding efficiency. The experiment results show that our codec achieves speedup factors of up to 100 with a performance loss of less than 0.1 dB. We use doublestimulus impairment scale scores to evaluate the perceptual quality of our approach for different levels of complexity. Index Terms—Fast algorithm, matching pursuit (MP), treebased vector quantization (VQ), video coding. I.
A framebased ratedistortion optimal coding system using a lower bound depthfirstsearch strategy
 in Proc. of Nordic Signal Processing Symposium
, 2002
"... The problem of finding the optimal set of quantized coefficients for a framebased encoded signal is known to be of very high complexity. This paper presents an efficient method of finding the operational RateDistortion (RD) optimal set of coefficients. The major complexity reduction lies in the r ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
The problem of finding the optimal set of quantized coefficients for a framebased encoded signal is known to be of very high complexity. This paper presents an efficient method of finding the operational RateDistortion (RD) optimal set of coefficients. The major complexity reduction lies in the reformulation of the original RDtradeoff problem, where a new set of coefficients is used as decision variables. These coefficients are connected to the orthogonalization of the set of selected frame vectors and not to the frame vectors themselves. Contrary to the original problem, the new problem is practicable to solve optimal in a reasonable amount of time. By organizing all possible solutions as nodes in a solution tree, we use complexity saving techniques to find the optimal solution in an even more efficient way. 1.
An alternating direction and projection algorithm for structureenforced matrix factorization
 2013 [Online]. Available: http://www.caam.rice.edu/yzhang/reports/tr1311.pdf
"... Structureenforced matrix factorization (SeMF) represents a large class of mathematical models appearing in various forms of principal component analysis, sparse coding, dictionary learning and other machine learning techniques useful in many applications including neuroscience and signal processi ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Structureenforced matrix factorization (SeMF) represents a large class of mathematical models appearing in various forms of principal component analysis, sparse coding, dictionary learning and other machine learning techniques useful in many applications including neuroscience and signal processing. In this paper, we present a unified algorithm framework, based on the classic alternating direction method of multipliers (ADMM), for solving a wide range of SeMF problems whose constraint sets permit lowcomplexity projections. We propose a strategy to adaptively adjust the penalty parameters which is the key to achieving good performance for ADMM. We conduct extensive numerical experiments to compare the proposed algorithm with a number of stateoftheart specialpurpose algorithms on test problems including dictionary learning for sparse representation and sparse nonnegative matrix factorization. Results show that our unified SeMF algorithm can solve different types of factorization problems as reliably and as efficiently as specialpurpose algorithms. In particular, our SeMF algorithm provides the ability to explicitly enforce various combinatorial sparsity patterns that, to our knowledge, has not been considered in existing approaches. 1
A Fully Automated Latent Fingerprint Matcher with Embedded Selflearning Segmentation Module
"... Latent fingerprint has the practical value to identify the suspects who have unintentionally left a trace of fingerprint in the crime scenes. However, designing a fully automated latent fingerprint matcher is a very challenging task as it needs to address many challenging issues including the separa ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
Latent fingerprint has the practical value to identify the suspects who have unintentionally left a trace of fingerprint in the crime scenes. However, designing a fully automated latent fingerprint matcher is a very challenging task as it needs to address many challenging issues including the separation of overlapping structured patterns over the partial and poor quality latent fingerprint image, and finding a match against a large background database that would have different resolutions. Currently there is no fully automated latent fingerprint matcher available to the public and most literature reports have utilized a specialized latent fingerprint matcher COTS3 which is not accessible to the public. This will make it infeasible to assess and compare the relevant research work which is vital for this research community. In this study, we target to develop a fully automated latent matcher for adaptive detection of the region of interest and robust matching of latent prints. Unlike the manually conducted matching procedure, the proposed latent matcher can run like a sealed black box without any manual intervention. This matcher consists of the following two modules: (i) the dictionary learningbased region of interest (ROI) segmentation scheme; and (ii) the genetic algorithm1 ar
Correspondence The CramérRao Bound for Estimating a Sparse Parameter Vector
"... Abstract—The goal of this contribution is to characterize the best achievable meansquared error (MSE) in estimating a sparse deterministic parameter from measurements corrupted by Gaussian noise. To this end, an appropriate definition of bias in the sparse setting is developed, and the constrained ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract—The goal of this contribution is to characterize the best achievable meansquared error (MSE) in estimating a sparse deterministic parameter from measurements corrupted by Gaussian noise. To this end, an appropriate definition of bias in the sparse setting is developed, and the constrained CramérRao bound (CRB) is obtained. This bound is shown to equal the CRB of an estimator with knowledge of the support set, for almost all feasible parameter values. Consequently, in the unbiased case, our bound is identical to the MSE of the oracle estimator. Combined with the fact that the CRB is achieved at high signaltonoise ratios signaltonoise ratio (SNRs) by the maximum likelihood technique, our result provides a new interpretation for the common practice of using the oracle estimator as a gold standard against which practical approaches are compared. Index Terms—Constrained estimation, CramérRao bound (CRB), sparse estimation. I.
Decomposition and Dictionary Learning for 3D Trajectories
"... A new model for describing a threedimensional (3D) trajectory is proposed in this article. The studied trajectory is viewed as a linear combination of rotatable 3D patterns. The resulting model is thus 3D rotation invariant (3DRI). Moreover, the temporal patterns are considered as shiftinvariant. ..."
Abstract
 Add to MetaCart
(Show Context)
A new model for describing a threedimensional (3D) trajectory is proposed in this article. The studied trajectory is viewed as a linear combination of rotatable 3D patterns. The resulting model is thus 3D rotation invariant (3DRI). Moreover, the temporal patterns are considered as shiftinvariant. This article is divided into two parts based on this model. On the one hand, the 3DRI decomposition estimates the active patterns, their coefficients, their rotations and their shift parameters. Based on sparse approximation, this is carried out by two nonconvex optimizations: 3DRI matching pursuit (3DRIMP) and 3DRI orthogonal matching pursuit (3DRIOMP). On the other hand, a 3DRI learning method learns the characteristic patterns of a database through a 3DRI dictionary learning algorithm (3DRIDLA). The proposed algorithms are first applied to simulation data to evaluate their performances and to compare them to other algorithms. Then, they are applied to real motion data of cued speech, to learn the 3D trajectory patterns characteristic of this gestural language.
Multivariate Temporal Dictionary Learning for EEG
, 2013
"... This article addresses the issue of representing electroencephalographic (EEG) signals in an efficient way. While classical approaches use a fixed Gabor dictionary to analyze EEG signals, this article proposes a datadriven method to obtain an adapted dictionary. To reach an efficient dictionary lea ..."
Abstract
 Add to MetaCart
This article addresses the issue of representing electroencephalographic (EEG) signals in an efficient way. While classical approaches use a fixed Gabor dictionary to analyze EEG signals, this article proposes a datadriven method to obtain an adapted dictionary. To reach an efficient dictionary learning, appropriate spatial and temporal modeling is required. Interchannels links are taken into account in the spatial multivariate model, and shiftinvariance is used for the temporal model. Multivariate learned kernels are informative (a few atoms code plentiful energy) and interpretable (the atoms can have a physiological meaning). Using real EEG data, the proposed method is shown to outperform the classical multichannel matching pursuit used with a Gabor dictionary, as measured by the representative power of the learned dictionary and its spatial flexibility. Moreover, dictionary learning can capture interpretable patterns: this ability is illustrated on real data, learning a P300 evoked potential.
Int J Comput Vis DOI 10.1007/s112630140755z Image Deblurring with Coupled Dictionary Learning
, 2014
"... Abstract Image deblurring is a challenging problem in vision computing. Traditionally, this task is addressed as an inverse problem that is enclosed into the image itself. This paper presents a learningbased framework where the knowledge hidden in huge amounts of available data is explored and exp ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract Image deblurring is a challenging problem in vision computing. Traditionally, this task is addressed as an inverse problem that is enclosed into the image itself. This paper presents a learningbased framework where the knowledge hidden in huge amounts of available data is explored and exploited for image deblurring. To this end, our algorithm is developed under the conceptual framework of coupled dictionary learning. Specifically, given pairs of blurred image patches and their corresponding clear ones, a learning model is constructed to learn a pair of dictionaries. Among them, one dictionary is responsible for the representation of clear images, while the other is responsible for that of the blurred images. Theoretically, the learning model is analyzed with coupled sparse representations for training samples. As the atoms of these dictionaries are coupled together onebyone, the reconstruction information can be transmitted between the clear and blurry images. In application phase, the blurry dictionary is employed to reconstruct linearly the blurry image to be restored. Then, the reconstruction coeffi
BTF Compression via Sparse Tensor Decomposition
"... In this paper, we present a novel compression technique for Bidirectional Texture Functions based on a sparse tensor decomposition. We apply the KSVD algorithm along two different modes of a tensor to decompose it into a small dictionary and two sparse tensors. This representation is very compact, ..."
Abstract
 Add to MetaCart
(Show Context)
In this paper, we present a novel compression technique for Bidirectional Texture Functions based on a sparse tensor decomposition. We apply the KSVD algorithm along two different modes of a tensor to decompose it into a small dictionary and two sparse tensors. This representation is very compact, allowing for considerably better compression ratios at the same RMS error than possible with current compression techniques like PCA, Nmode SVD and Per Cluster Factorization. In contrast to other tensor decomposition based techniques, the use of a sparse representation achieves a rendering performance that is at high compression ratios similar to PCA based methods. Categories and Subject Descriptors (according to ACM CCS): I.3.7 [Computer Graphics]: ThreeDimensional Graphics and Realism—Color, shading, shadowing, and texture