检索结果-内蒙古大学图书馆

sparse coding on Symmetric Positive Definite Manifolds Using Bregman Divergences

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2016年第6期27卷 1294-1306页

作者： Harandi, Mehrtash T. Hartley, Richard Lovell, Brian Sanderson, Conrad Canberra Res Lab NICTA Comp Vis Res Grp Canberra ACT 2601 Australia Australian Natl Univ Coll Engn & Comp Sci GPO Box 4 Canberra ACT 0200 Australia Univ Queensland Brisbane Qld 4072 Australia Queensland Res Lab NICTA Brisbane Qld 4000 Australia

This paper introduces sparse coding and dictionary learning for symmetric positive definite (SPD) matrices, which are often used in machine learning, computer vision, and related areas. Unlike traditional sparse coding schemes that work in vector spaces, in this paper, we discuss how SPD matrices can be described by sparse combination of dictionary atoms, where the atoms are also SPD matrices. We propose to seek sparse coding by embedding the space of SPD matrices into the Hilbert spaces through two types of the Bregman matrix divergences. This not only leads to an efficient way of performing sparse coding but also an online and iterative scheme for dictionary learning. We apply the proposed methods to several computer vision tasks where images are represented by region covariance matrices. Our proposed algorithms outperform state-of-the-art methods on a wide range of classification tasks, including face recognition, action recognition, material classification, and texture categorization.

关键词： Bregman's divergences dictionary learning kernel methods Riemannian's geometry sparse coding

来源：评论

学校读者我要写书评

暂无评论

sparse coding and Dictionary Learning with Linear Dynamical Systems

Sparse Coding and Dictionary Learning with Linear Dynamical ...

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Wenbing Huang Fuchun Sun Lele Cao Deli Zhao Huaping Liu Mehrtash Harandi Dept. of Comput. Sci. & Technol. Tsinghua Univ. Beijing China State Key Lab. of Intell. Technol. & Syst. Tsinghua Nat. Lab. for Inf. Sci. & Technol. Beijing China NICTA Australian Nat. Univ. Canberra ACT Australia

ISBN: (纸本)9781467388528

Linear Dynamical Systems (LDSs) are the fundamental tools for encoding spatio-temporal data in various disciplines. To enhance the performance of LDSs, in this paper, we address the challenging issue of performing sparse coding on the space of LDSs, where both data and dictionary atoms are LDSs. Rather than approximate the extended observability with a finite-order matrix, we represent the space of LDSs by an infinite Grassmannian consisting of the orthonormalized extended observability subspaces. Via a homeomorphic mapping, such Grassmannian is embedded into the space of symmetric matrices, where a tractable objective function can be derived for sparse coding. Then, we propose an efficient method to learn the system parameters of the dictionary atoms explicitly, by imposing the symmetric constraint to the transition matrices of the data and dictionary systems. Moreover, we combine the state covariance into the algorithm formulation, thus further promoting the performance of the models with symmetric transition matrices. Comparative experimental evaluations reveal the superior performance of proposed methods on various tasks including video classification and tactile recognition.

关键词： Observability Dictionaries Encoding Symmetric matrices sparse matrices Measurement Computational modeling Dictionaries as Topic Symmetric matrix Observability DYNAMICAL SYSTEMS sparse coding sparse matrix Computational modeling coding S matrix system parameter

来源：评论

学校读者我要写书评

暂无评论

sparse coding with Anomaly Detection

引用

JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY 2015年第2期79卷 179-188页

作者： Adler, Amir Elad, Michael Hel-Or, Yacov Rivlin, Ehud Technion Israel Inst Technol Dept Comp Sci IL-32000 Haifa Israel Interdisciplinary Ctr Dept Comp Sci Herzliyya Israel

We consider the problem of simultaneous sparse coding and anomaly detection in a collection of data vectors. The majority of the data vectors are assumed to conform with a sparse representation model, whereas the anomaly is caused by an unknown subset of the data vectors-the outliers-which significantly deviate from this model. The proposed approach utilizes the Alternating Direction Method of Multipliers (ADMM) to recover simultaneously the sparse representations and the outliers components for the entire collection. This approach provides a unified solution both for jointly sparse and independently sparse data vectors. We demonstrate the usefulness of the proposed approach for irregular heartbeats detection in Electrocardiogram (ECG) as well as for specular reflectance and shadows removal from natural images.

关键词： sparse coding Anomaly detection ADMM Arrythmia detection Specular reflectance removal Shadows removal

来源：评论

学校读者我要写书评

暂无评论

sparse coding of hyperspectral imagery using online learning

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2015年第4期9卷 959-966页

作者： Ulku, Irem Toreyin, Behcet Ugur Cankaya Univ Dept Elect & Elect Engn TR-06790 Ankara Turkey Sci & Technol Res Council Turkey TUBITAK Space Technol Inst UZAY TR-06800 Ankara Turkey

sparse coding ensures to express the data in terms of a few nonzero dictionary elements. Since the data size is large for hyperspectral imagery, it is reasonable to use sparse coding for compression of hyperspectral images. In this paper, a hyperspectral image compression method is proposed using a discriminative online learning-based sparse coding algorithm. Compression and anomaly detection tests are performed on hyperspectral images from the AVIRIS dataset. Comparative rate-distortion analyses indicate that the proposed method is superior to the state-of-the-art hyperspectral compression techniques.

关键词： sparse coding Hyperspectral imagery Anomaly detection Online learning

来源：评论

学校读者我要写书评

暂无评论

sparse coding for Third-order Super-symmetric Tensor Descriptors with Application to Texture Recognition

Sparse Coding for Third-order Super-symmetric Tensor Descrip...

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Piotr Koniusz Anoop Cherian National ICT Australia (NICTA) Canberra Research Laboratory ARC Centre of Excellence for Robotic Vision Australian National University

ISBN: (纸本)9781467388528

Super-symmetric tensors - a higher-order extension of scatter matrices - are becoming increasingly popular in machine learning and computer vision for modeling data statistics, co-occurrences, or even as visual descriptors. They were shown recently to outperform second-order approaches [18], however, the size of these tensors are exponential in the data dimensionality, which is a significant concern. In this paper, we study third-order super-symmetric tensor descriptors in the context of dictionary learning and sparse coding. For this purpose, we propose a novel non-linear third-order texture descriptor. Our goal is to approximate these tensors as sparse conic combinations of atoms from a learned dictionary. Apart from the significant benefits to tensor compression that this framework offers, our experiments demonstrate that the sparse coefficients produced by this scheme lead to better aggregation of high-dimensional data and showcase superior performance on two common computer vision tasks compared to the state of the art.

关键词： sparse coding Tensor images computer vision state of the art Subject Headings Descriptors Dictionaries as Topic

来源：评论

学校读者我要写书评

暂无评论

Brain tumor classification and segmentation using sparse coding and dictionary learning

引用

BIOMEDICAL ENGINEERING-BIOMEDIZINISCHE TECHNIK 2016年第4期61卷 413-429页

作者： Al-Shaikhli, Saif Dawood Salman Yang, Michael Ying Rosenhahn, Bodo Leibniz Univ Hannover Inst Informat Proc Appelstr 9A D-30167 Hannover Germany Tech Univ Dresden Comp Vis Lab Dresden Germany

This paper presents a novel fully automatic framework for multi-class brain tumor classification and segmentation using a sparse coding and dictionary learning method. The proposed framework consists of two steps: classification and segmentation. The classification of the brain tumors is based on brain topology and texture. The segmentation is based on voxel values of the image data. Using K-SVD, two types of dictionaries are learned from the training data and their associated ground truth segmentation: feature dictionary and voxel-wise coupled dictionaries. The feature dictionary consists of global image features (topological and texture features). The coupled dictionaries consist of coupled information: gray scale voxel values of the training image data and their associated label voxel values of the ground truth segmentation of the training data. For quantitative evaluation, the proposed framework is evaluated using different metrics. The segmentation results of the brain tumor segmentation (MICCAI-BraTS-2013) database are evaluated using five different metric scores, which are computed using the online evaluation tool provided by the BraTS-2013 challenge organizers. Experimental results demonstrate that the proposed approach achieves an accurate brain tumor classification and segmentation and outperforms the state-of-the-art methods.

关键词： brain tumor classification dictionary learning segmentation sparse coding texture topology

来源：评论

学校读者我要写书评

暂无评论

Real-time Fabric Defect Detection Using Accelerated Small-scale Over-completed Dictionary of sparse coding

引用

INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS 2016年第1期13卷 1-1页

作者： Feng, Tianpeng Zou, Lian Yan, Jia Shi, Wenxuan Liu, Yifeng Fan, Cien Deng, Dexiang Wuhan Univ Wuhan 430072 Peoples R China

An auto fabric defect detection system via computer vision is used to replace manual inspection. In this paper, we propose a hardware accelerated algorithm based on a small-scale over-completed dictionary (SSOCD) via sparse coding (SC) method, which is realized on a parallel hardware platform (TMS320C6678). In order to reduce computation, the image patches projections in the training SSOCD are taken as features and the proposed features are more robust, and exhibit obvious advantages in detection results and computational cost. Furthermore, we introduce detection ratio and false ratio in order to measure the performance and reliability of the hardware accelerated algorithm. The experiments show that the proposed algorithm can run with high parallel efficiency and that the detection speed meets the real-time requirements of industrial inspection.

关键词： Fabric Defect Detection sparse coding Hardware Acceleration

来源：评论

学校读者我要写书评

暂无评论

Dictionary Learning for sparse coding: Algorithms and Convergence Analysis

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2016年第7期38卷 1356-69页

作者： Bao, Chenglong Ji, Hui Quan, Yuhui Shen, Zuowei Natl Univ Singapore Dept Math Singapore 119076 Singapore

In recent years, sparse coding has been widely used in many applications ranging from image processing to pattern recognition. Most existing sparse coding based applications require solving a class of challenging non-smooth and non-convex optimization problems. Despite the fact that many numerical methods have been developed for solving these problems, it remains an open problem to find a numerical method which is not only empirically fast, but also has mathematically guaranteed strong convergence. In this paper, we propose an alternating iteration scheme for solving such problems. A rigorous convergence analysis shows that the proposed method satisfies the global convergence property: the whole sequence of iterates is convergent and converges to a critical point. Besides the theoretical soundness, the practical benefit of the proposed method is validated in applications including image restoration and recognition. Experiments show that the proposed method achieves similar results with less computation when compared to widely used methods such as K-SVD.

关键词： Dictionary learning sparse coding non-convex optimization convergence analysis

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Compression Techniques – The sparse coding and BWT

引用

Procedia Computer Science 2016年 92卷 106-111页

作者： Annapurna Pradhan Nibedita Pati Suvendu Rup Avipsa S. Panda Lalit Kumar Kanoje Trident Academy of Technology Bhubaneswar 751021 India IIIT Bhubaneswar India

The process of image compression has been the most researched area for decades. Image compression is a necessity for the transmission of images and the storage of images in an efficient manner. This is because image compression represents image having less correlated pixels, eliminates redundancy and also removes irrelevant pixels. The most commonly known techniques for image compression are JPEG and JPEG 2000. But these two have certain drawbacks and thus various other techniques have been popping up, of late. Recently, a growing interest has been marked for the use of basis selection algorithms for signal approximation and compression. In the recent past, the orthogonal and bi-orthogonal complete dictionaries (like the Discrete Cosine Transform (DCT) or wavelets) have been the dominant transform domain representations. But, the DCT and the wavelet transform techniques experience blocking and ringing artefacts and also these are not capable of capturing directional information. Hence, sparse coding method (by Orthogonal Matching Pursuit (OMP) algorithm) comes into picture. Another, novel technique that has taken up recent interests of the image compression area is the Burrows-Wheeler transform (BWT). BWT is generally applied prior to entropy encoding for a better regularity structure. The paper puts forth the comparison results of the methods of sparse approximation and BWT. The comparison analysis was done using the two techniques on various images, out of which one has been given in the paper.

关键词： image compression BWT sparse coding orthogonal matching pursuit MTF coding

来源：评论

学校读者我要写书评

暂无评论

Refining sparse coding Sub-word Unit Inventories with Lattice-constrained Viterbi Training

引用

Procedia Computer Science 2016年 81卷 87-94页

作者： Wiehan Agenbag Thomas Niesler Department of Electrical and Electronic Engineering Stellenbosch University Stellenbosch South Africa

We investigate the application of two novel lattice-constrained Viterbi training strategies to the task of improving sub-word unit (SWU) inventories that were discovered using an unsupervised sparse coding approach. The automatic determination of these SWUs remain a critical and unresolved obstacle to the development of ASR for under-resourced languages. The first lattice-constrained training strategy attempts to jointly learn a bigram SWU language model along with the evolving SWU inventory. We find that this substantially increases correspondence with expert-defined reference phonemes on the TIMIT dataset, but does little to improve pronunciation consistency. The second approach attempts to jointly infer an SWU pronunciation model for each word in the training vocabulary, and to constrain transcription using these models. We find that this lightly supervised approach again substantially increases correspondence with the reference phonemes, and in this case also improves pronunciation consistency.

关键词： segmentation clustering sparse coding sub-word units Viterbi training

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：