检索结果-内蒙古大学图书馆

Robust Content Fingerprinting Algorithm Based on sparse coding

IEEE SIGNAL PROCESSING LETTERS 2015年第9期22卷 1254-1258页

作者： Li, Yue Nan Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China

Content fingerprinting is a powerful solution for media indexing, searching and digital right management, in which the perceptual content of digital media is summarized to a robust and discriminative digest. In this letter, we develop a general paradigm for image fingerprinting by exploiting the capability of sparse coding in capturing the visual characteristics of digital image. Furthermore, the impact of the dictionary for sparse coding on the performance of fingerprinting algorithm is analyzed. Accordingly, the problem of dictionary learning is studied in the context of content fingerprinting by incorporating the robustness and discriminability requirements. Comparative experiments indicate that the proposed work exhibits much higher content identification accuracy than the state-of-the-art ones, and the dictionary learned by the proposed work can substantially improve the performance of fingerprinting algorithm. In addition, our algorithm is highly efficient, and its average fingerprint computation time is less than 0.024s.

关键词： Content identification image fingerprinting robust hashing sparse coding

来源：评论

学校读者我要写书评

暂无评论

Taiwan Sign Language Recognition System Using LC-KSVD sparse coding Method

Taiwan Sign Language Recognition System Using LC-KSVD Sparse...

引用

2016 6th International Conference on Machinery,Materials,Environment,Biotechnology and Computer(MMEBC 2016)

作者： Ching-Tang Hsieh Hsing-Che Liou Li-Ming Chen Dept.of Electrical and Computer Engineering Tamkang University

Sign language, for deaf-impaired people, plays an important role in communicationIn this paper, we devise a Taiwan Sign Language recognition systemWe use the Kinect2 sensor to get data from 94 sign morphemes shown once by 4 people, and extract hand shape features and trajectory features from depth images and joints of the body skeletonFinally, we have each sign morpheme dictionary trained by label consistent K-SVD(LC-KSVD) sparse coding algorithm for recognitionExperiments show our system performs well and the accuracy achieves 99.47% in close test.

关键词： Sign Language Recognition System sparse coding LC-KSVD

来源：评论

学校读者我要写书评

暂无评论

Multiple graph regularized sparse coding and multiple hypergraph regularized sparse coding for image representation

引用

NEUROCOMPUTING 2015年 154卷 245-256页

作者： Jin, Taisong Yu, Zhengtao Li, Lingling Li, Cuihua Xiamen Univ Dept Comp Sci Sch Informat Sci & Engn Xiamen 361005 Peoples R China Sci & Technol Electroopt Control Lab Luoyang 471009 Peoples R China Kunming Univ Sci & Technol Sch Informat Engn & Automat Kunming 650500 Peoples R China Zhengzhou Inst Aeronaut Ind Management Dept Comp Sci & Applicat Zhengzhou 450015 Peoples R China

Manifold regularized sparse coding shows promising performance for various applications. The key issue that must be considered in the application is how to adaptively select the suitable graph hyper-parameters in manifold learning for the sparse coding task. Usually, cross validation is applied, but it does not necessarily scale up and easily leads to overfitting. In this article, multiple graph sparse coding (MGrSc) and multiple Hypergraph sparse coding (MHGrSc) for image representation are proposed. Inspired by the Ensemble Manifold Regularizer, we formulate multiple graph and multiple Hypergraph regularizers to guarantee the smoothness of sparse codes along the geodesics of a data manifold, which is characterized by fusing the multiple previously given graph Laplacians or Hypergraph Laplacians. Then, the proposed regularziers, respectively, are incorporated into the traditional sparse coding framework, which results in two unified objective functions of sparse coding. Alternating optimization is used to optimize the objective functions, and two, novel manifold regularized sparse coding algorithms are presented. The proposed two sparse coding methods learn both the composite manifold and the sparse coding jointly, and it is fully automatic for learning the graph hyper-parameters in the manifold learning. Image clustering tests on real world datasets demonstrated that the proposed sparse coding methods are superior to the state-of-the-art methods. (C) 2014 Elsevier B.V. All rights reserved.

关键词： sparse coding Graph Hypergraph Alternating optimization

来源：评论

学校读者我要写书评

暂无评论

Compact sparse coding for Ground-Based Cloud Classification

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2015年第11期E98D卷 2003-2007页

作者： Liu, Shuang Zhang, Zhong Cao, Xiaozhong Tianjin Normal Univ Coll Elect & Commun Engn Tianjin Peoples R China CMA Meteorol Observat Ctr Beijing Peoples R China

Although sparse coding has emerged as an extremely powerful tool for texture and image classification, it neglects the relationship of coding coefficients from the same class in the training stage, which may cause a decline in the classification performance. In this paper, we propose a novel coding strategy named compact sparse coding for ground-based cloud classification. We add a constraint on coding coefficients into the objective function of traditional sparse coding. In this way, coding coefficients from the same class can be forced to their mean vector, making them more compact and discriminative. Experiments demonstrate that our method achieves better performance than the state-of-the-art methods.

关键词： ground-based cloud classification sparse coding compact sparse coding

来源：评论

学校读者我要写书评

暂无评论

A Supervised Classification Approach for Pol SAR Images Based on Covariance Matrix sparse coding

A Supervised Classification Approach for Pol SAR Images Base...

引用

2016 IEEE 13th International Conference on Signal Processing（ICSP2016）

作者： Neng Zhong Tianheng Yan Wen Yang Gui-Song Xia Signal Processing Lab School of Electronic InformationWuhan University The State Key Laboratory for Information Engineering in Surveying Mapping and Remote Sensing (LIESMARS)

To achieve the aim of classification for polarimetric synthetic aperture radar(Pol SAR) images, the supervised classification approach based on sparse coding of covariance matrix is proposed in this paper. Being different from traditional classification methods which are based on polarization features extraction or statistical distribution models, our method research the sparse coding algorithm for covariance matrices under the circumstances of Riemannian manifold. The proposed method first obtains the coding dictionary by using k-means clustering. Then, each covariance matrix is decomposed into the sparse linear combination of those atoms in the coding dictionary via Riemannian sparse coding approach. Finally, the sparse coding coefficients are used as the feature vectors to obtain the final classification results with support vector machine(SVM) classifier. The experimental results of different real Pol SAR images demonstrate that our method is effectiveness.

关键词： PolSAR image sparse coding supervised classification SVM

来源：评论

学校读者我要写书评

暂无评论

A linear approach for sparse coding by a two-layer neural network

引用

NEUROCOMPUTING 2015年第PartC期149卷 1315-1323页

作者： Montalto, Alessandro Tessitore, Giovanni Prevete, Roberto Univ Ghent Data Anal Dept Ghent Belgium Univ Naples Federico II Dept Phys Sci Naples Italy Univ Naples Federico II DIETI Naples Italy

Many approaches to transform classification problems from non-linear to linear by feature transformation have been recently presented in the literature. These notably include sparse coding methods and deep neural networks. However, many of these approaches require the repeated application of a learning process upon the presentation of unseen data input vectors, or else involve the use of large numbers of parameters and hyper-parameters, which must be chosen through cross-validation, thus increasing running time dramatically. In this paper, we propose and experimentally investigate a new approach for the purpose of overcoming limitations of both kinds. The proposed approach makes use of a linear auto-associative network (called SCNN) with just one hidden layer. The combination of this architecture with a specific error function to be minimized enables one to learn a linear encoder computing a sparse code which turns out to be as similar as possible to the sparse coding that one obtains by re-training the neural network. Importantly, the linearity of SCNN and the choice of the error function allow one to achieve reduced running time in the learning phase. The proposed architecture is evaluated on the basis of two standard machine learning tasks. Its performances are compared with those of recently proposed non-linear auto-associative neural networks. The overall results suggest that linear encoders can be profitably used to obtain sparse data representations in the context of machine learning problems, provided that an appropriate error function is used during the learning phase. (c) 2014 Elsevier B.V. All rights reserved.

关键词： Neural networks sparse coding Linear approach Encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Dictionary evaluation and optimization for sparse coding based speech processing

引用

INFORMATION SCIENCES 2015年 310卷 77-96页

作者： He, Yongjun Chen, Deyun Sun, Guanglu Han, Jiqing Harbin Univ Sci & Technol Harbin 150080 Peoples R China Harbin Inst Technol Harbin 150001 Peoples R China

Recently, sparse coding has attracted considerable attention in speech processing. As a promising technique, sparse coding can be widely used for analysis, representation, compression, denoising and separation of speech. To represent signals accurately and sparsely, a good dictionary which contains elemental signals is preferred and many methods have been propesed to learn such a dictionary. However, there is a lack of reasonable evaluation methods to judge whether a dictionary is good enough. To solve this problem, we define a group of measures for dictionary evaluation. These measures not only address sparseness and reconstruction error of signal representation, but also consider denoising and separating performance. We show how to evaluate dictionaries with these measures, and further propose two methods to optimize dictionaries by improving relative measures. The first method improves the efficiency of sparse coding by removing unimportant atoms;the second one improves denoising performance of dictionaries by removing harmful atoms. Experimental results show that the measures can provide reasonable evaluations and the proposed methods for optimization can further improve given dictionaries. (C) 2015 Published by Elsevier Inc.

关键词： sparse coding Speech denoising Dictionary evaluation Dictionary optimization Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Order Preserving sparse coding

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2015年第8期37卷 1615-1628页

作者： Ni, Bingbing Moulin, Pierre Yan, Shuicheng Adv Digital Sci Ctr Singapore 138632 Singapore Univ Illinois Dept Elect & Comp Engn Beckman Inst Urbana IL 61801 USA Natl Univ Singapore Dept Elect & Comp Engn Singapore 117576 Singapore

In this paper, we investigate order-preserving sparse coding for classifying structured data whose atomic features possess ordering relationships. Examples include time sequences where individual frame-wise features are temporally ordered, as well as still images (landscape, street view, etc.) where different regions of the image are spatially ordered. Classification of these structured data is often tackled by first decomposing the input data into individual atomic features, then performing sparse coding or other processing for each atomic feature vector independently, and finally aggregating individual responses to classify the input data. However, this heuristic approach ignores the underlying order of the individual atomic features within the input data, and results in suboptimal discriminative capability. In this work, we introduce an order preserving regularizer which aims to preserve the ordering structure of the reconstruction coefficients within the sparse coding framework. An efficient Nesterov-type smooth approximation method is developed for optimization of the new regularization criterion, with theoretically guaranteed error bound. We perform extensive experiments for time series classification on a synthetic dataset, several machine learning benchmarks, and an RGB-D human activity dataset. We also report experiments for scene classification on a benchmark image dataset. The encoded representation is discriminative and robust, and our classifier outperforms state-of-the-art methods on these tasks.

关键词： sparse coding order preserving time sequence classification scene classification

来源：评论

学校读者我要写书评

暂无评论

Action Recognition in Video Using sparse coding and Relative Features

Action Recognition in Video Using Sparse Coding and Relative...

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Anali Alfaro Domingo Mery Alvaro Soto P. Universidad Catolica de Chile

ISBN: (纸本)9781467388528

This work presents an approach to category-based action recognition in video using sparse coding techniques. The proposed approach includes two main contributions: i) A new method to handle intra-class variations by decomposing each video into a reduced set of representative atomic action acts or key-sequences, and ii) A new video descriptor, ITRA: Inter-Temporal Relational Act Descriptor, that exploits the power of comparative reasoning to capture relative similarity relations among key-sequences. In terms of the method to obtain key-sequences, we introduce a loss function that, for each video, leads to the identification of a sparse set of representative key-frames capturing both, relevant particularities arising in the input video, as well as relevant generalities arising in the complete class collection. In terms of the method to obtain the ITRA descriptor, we introduce a novel scheme to quantify relative intra and inter-class similarities among local temporal patterns arising in the videos. The resulting ITRA descriptor demonstrates to be highly effective to discriminate among action categories. As a result, the proposed approach reaches remarkable action recognition performance on several popular benchmark datasets, outperforming alternative state-of-the-art techniques by a large margin.

关键词： Videotapes sparse coding Descriptors Recognition (Psychology)

来源：评论

学校读者我要写书评

暂无评论

A sparse coding Neural Network ASIC With On-Chip Learning for Feature Extraction and Encoding

引用

IEEE JOURNAL OF SOLID-STATE CIRCUITS 2015年第4期50卷 1070-1079页

作者： Knag, Phil Kim, Jung Kuk Chen, Thomas Zhang, Zhengya Univ Michigan Dept Elect Engn & Comp Sci Ann Arbor MI 48109 USA

Hardware-based computer vision accelerators will be an essential part of future mobile devices to meet the low power and real-time processing requirement. To realize a high energy efficiency and high throughput, the accelerator architecture can be massively parallelized and tailored to vision processing, which is an advantage over software-based solutions and general-purpose hardware. In this work, we present an ASIC that is designed to learn and extract features from images and videos. The ASIC contains 256 leaky integrate-and-fire neurons connected in a scalable two-layer network of 8 8 grids linked in a 4-stage ring. sparse neuron activation and the relatively small grid keep the spike collision probability low to save access arbitration. The weight memory is divided into core memory and auxiliary memory, such that the auxiliary memory is only powered on for learning to save inference power. High-throughput inference is accomplished by the parallel operation of neurons. Efficient learning is implemented by passing parameter update messages, which is further simplified by an approximation technique. A 3.06 mm 65 nm CMOS ASIC test chip is designed to achieve a maximum inference throughput of 1.24 Gpixel/s at 1.0 V and 310 MHz, and on-chip learning can be completed in seconds. To improve the power consumption and energy efficiency, core memory supply voltage can be reduced to 440 mV to take advantage of the error resilience of the algorithm, reducing the inference power to 6.67 mW for a 140 Mpixel/s throughput at 35 MHz.

关键词： Feature extraction hardware acceleration neural network architecture sparse coding sparse and independent local network

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：