检索结果-内蒙古大学图书馆

Simple Method for High-Performance Digit Recognition Based on sparse coding

IEEE TRANSACTIONS ON NEURAL NETWORKS 2008年第11期19卷 1985-1989页

作者： Labusch, Kai Barth, Erhardt Martinetz, Thomas Med Univ Lubeck Inst Neuro & Bioinformat D-23538 Lubeck Germany

In this brief paper, we propose a method of feature extraction for digit recognition that is inspired by vision research: a sparse-coding strategy and a local maximum operation. We show that our method, despite its simplicity, yields state-of-the-art classification results on a highly competitive digit-recognition benchmark. We first employ the unsupervised sparsenet algorithm to learn a basis for representing patches of handwritten digit images. We then use this basis to extract local coefficients. In a second step, we apply a local maximum operation to implement local shift invariance. Finally, we train a support vector machine (SVM) on the resulting feature vectors and obtain state-of-the-art classification performance in the digit recognition task defined by the MNIST benchmark. We compare the different classification performances obtained with sparse coding, Gabor wavelets, and principal component analysis (PCA). We conclude that the learning of a sparse representation of local image patches combined with a local maximum operation for feature extraction can significantly improve recognition performance.

关键词： Digit recognition feature extraction sparse coding support vector machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

A NOVEL SUPERVISED STRUCTURE DICTIONARY LEARNING FOR CLASSIFICATION BASED ON sparse REPRESENTATION

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2012年第7期26卷 1255012-1255012页

作者： Tang, Xin Wang, Patrick S. Feng, Guocan Sun Yat Sen Univ Sch Math & Computat Sci Guangzhou 510275 Guangdong Peoples R China Northeastern Univ CCIS Boston MA USA ECNU Shanghai Peoples R China

sparse representation based classification has led to interesting image recognition results, while the dictionary used for sparse coding plays a key role in it. This paper presents a novel supervised structure dictionary learning (SSDL) algorithm to learn a discriminative and block structure dictionary. We associate label information with each dictionary item and make each class-specific sub-dictionary in the whole structured dictionary have good representation ability to the training samples from the associated class. More specifically, we learn a structured dictionary and a multiclass classifier simultaneously. Adding an inhomogeneous representation term to the objective function and considering the independence of the class-specific sub-dictionaries improve the discrimination capabilities of the sparse coordinates. An iteratively optimization method be proposed to solving the new formulation. Experimental results on four face databases demonstrate that our algorithm outperforms recently proposed competing sparse coding methods.

关键词： Dictionary learning sparse coding structure dictionary proximal method

来源：评论

学校读者我要写书评

暂无评论

A robust super resolution method for video

A robust super resolution method for video

引用

Asilomar Conference on Signals, Systems & Computers

作者： Nafise Barzigar Aminmohammad Roozgard Samuel Cheng Pramode Verma Department of Electrical and Computer Engineering University of Oklahoma Tulsa OK USA

ISBN: (纸本)9781467350501

Super resolution reconstruction produces a higher resolution image based on a set of low resolution images, taken from the same scene. Recently, many papers have been published, proposing a variety algorithms of video super resolution. This paper presents a new approach to video super resolution, based on sparse coding and belief propagation. First, find the candidate pixels on multiple frames using sparse coding and belief propagation. Second, exploit the similarities of candidate pixels using the Non-local Means method to average out the noise among similar patches. The experimental results show the effectiveness of our method and demonstrate its robustness to other super resolution methods.

关键词： Super Resolution sparse coding Belief Propagation Non-Local Means Filter

来源：评论

学校读者我要写书评

暂无评论

Visual Saliency Detection Based on Deredundancy and Global Contrast

Visual Saliency Detection Based on Deredundancy and Global C...

引用

The 2nd International Conference on Computer-Aided Design, Manufacturing, Modeling and Simulation(CDMMS 2012)

作者： Huan Shen Xiaodong Miao Yunsheng Tan College of Energy & Power Engineering Nanjing University of Aeronautics and Astronautics

ISBN: (纸本)9783037855409

A new method for saliency detection is *** on the sparse coding model,we propose a power spectral filter to eliminate the second-order residual correlation,which suppress the global repeated items *** addition,aim to modeling the mechanism of the human retina prior response to high-contrast stimuli,the effect of color context is *** result indicates that our method has high-quality detection performance with respect to the ability not only to highlight the salient objects in complex environment but also to pop up them uniformly.

关键词： Image Processing Machine Vision Visual Attention sparse coding

来源：评论

学校读者我要写书评

暂无评论

HVS based dictionary learning for scalable sparse image representation

HVS based dictionary learning for scalable sparse image repr...

引用

Asilomar Conference on Signals, Systems & Computers

作者： Bojana Begovic Vladimir Stankovic Lina Stankovic Samuel Cheng Department EEE University of Strathclyde UK School of Electrical and Compo Engineering University of Oklahoma USA

ISBN: (纸本)9781467350501

A novel dictionary learning design, driven by the Human Visual System (HVS) perception characteristic, for scalable representation of natural images is proposed. It builds upon the K-SVD algorithm, which learns non-scalable dictionaries for natural images. We introduce regularization over the K-SVD dictionary atom update stage, enabling scalable sparse image reconstruction. Mainly, emphasis is on the dictionary's low and high spatial frequency components. Experimental results demonstrate the practicality of the proposed scheme for effective scalable sparse recovery of dynamic data changing over time (e.g., video). For the aforementioned purpose the proposed method outperforms the conventional K-SVD algorithm on average by 10.8[dB].

关键词： scalable video representation sparse coding regularization

来源：评论

学校读者我要写书评

暂无评论

Discriminatively Trained sparse Code Gradients for Contour Detection 12

Discriminatively Trained Sparse Code Gradients for Contour D...

引用

Annual Conference on Neural Information Processing Systems

作者： Xiaofeng Ren Liefeng Bo Intel Science and Technology Center for Pervasive Computing Intel Labs Seattle WA 98195 USA

ISBN: (纸本)9781627480031

Finding contours in natural images is a fundamental problem that serves as the basis of many tasks such as image segmentation and object recognition. At the core of contour detection technologies are a set of hand-designed gradient features, used by most approaches including the state-of-the-art Global Pb (gPb) operator. In this work, we show that contour detection accuracy can be significantly improved by computing sparse Code Gradients (SCG), which measure contrast using patch representations automatically learned through sparse coding. We use K-SVD for dictionary learning and Orthogonal Matching Pursuit for computing sparse codes on oriented local neighborhoods, and apply multi-scale pooling and power transforms before classifying them with linear SVMs. By extracting rich representations from pixels and avoiding collapsing them prematurely, sparse Code Gradients effectively learn how to measure local contrasts and find contours. We improve the F-measure metric on the BSDS500 benchmark to 0.74 (up from 0.71 of gPb contours). Moreover, our learning approach can easily adapt to novel sensor data such as Kinect-style RGB-D cameras: sparse Code Gradients on depth maps and surface normals lead to promising contour detection using depth and depth+color, as verified on the NYU Depth Dataset.

关键词： contour detection Outlines contour Codes surface normal sparse coding matching pursuits Sensor Data object recognition image segmentation pixel

来源：评论

学校读者我要写书评

暂无评论

Image Denoising and Inpainting with Deep Neural Networks 12

Image Denoising and Inpainting with Deep Neural Networks

引用

Annual Conference on Neural Information Processing Systems

作者： Junyuan Xie Linli Xu Enhong Chen School of Computer Science and Technology University of Science and Technology of China

ISBN: (纸本)9781627480031

We present a novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA). We propose an alternative training scheme that successfully adapts DA, originally designed for unsupervised feature learning, to the tasks of image denoising and blind inpainting. Our method's performance in the image denoising task is comparable to that of KSVD which is a widely used sparse coding technique. More importantly, in blind image inpainting task, the proposed method provides solutions to some complex problems that have not been tackled before. Specifically, we can automatically remove complex patterns like superimposed text from an image, rather than simple patterns like pixels missing at random. Moreover, the proposed method does not need the information regarding the region that requires inpainting to be given a priori. Experimental results demonstrate the effectiveness of the proposed method in the tasks of image denoising and blind inpainting. We also show that our new training scheme for DA is more effective and can improve the performance of unsupervised feature learning.

关键词： image denoising inpaint sparse coding DOE DESIGN AGENCY designer's alterations DA Religious Missions Blind Imagery (Psychotherapy) images pixel

来源：评论

学校读者我要写书评

暂无评论

sparse Representation based on Matrix Rank Minimization and K-Means Clustering for Recognition

Sparse Representation based on Matrix Rank Minimization and ...

引用

International Joint Conference on Neural Networks

作者： Long Ma Chunheng Wang Baihua Xiao State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China 100190

ISBN: (纸本)9781467314886

In this paper, we propose a sparse coding algorithm based on matrix rank minimization and k-means clustering and for recognition. We consider the problem of removing the noise in the training samples and generating more samples at the same time. To accomplish this, we extended the matrix rank minimization problem to cope with complex data. Samples from the same class are segmented into several groups by k-means clustering algorithm, and matrix rank minimization is applied on the clustered data to separate the noises and recover the low-rank structures in the grouped data. An over-complete dictionary is constructed by connecting the low-rank structures and the training samples together to keep the samples diversity. sparse representation is operated based on this over-complete dictionary for recognition. Furthermore, a parameter is introduced to adjust the weighting of the coefficients that code the noises. We apply the proposed algorithm for character and face recognition. Experiments with improved performances validate the effectiveness of the proposed algorithm.

关键词： sparse representation Noise Recognition (Psychology) Rank of data matrices sparse coding Dictionaries as Topic

来源：评论

学校读者我要写书评

暂无评论

Visual tracking using sparse representation

Visual tracking using sparse representation

引用

IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)

作者： Amir H. Feghahati Amin Jourabloo Mansour Jamzad Mohammad T. Manzuri-Shalmani Department of Compo Engineering Sharif University of Technology Iran

ISBN: (纸本)9781467356053

In this work we present a sparse dictionary learning method, specifically tuned to solve the tracking problem. Recently, sparse representation has drawn much attention because of its genuineness and strong mathematical background. In this paper we present an online method for dictionary learning which is desirable for problems such as tracking. Online learning methods are preferable because the whole data are not available at the current time. The presented method tries to use the advantages of the generative and discriminative models to achieve better performance. The experimental results show our method can overcome many tracking challenges.

关键词： Visual Tracking sparse Representation sparse coding Dictionary Learning

来源：评论

学校读者我要写书评

暂无评论

SPARSITY LEVEL IN A NON-NEGATIVE MATRIX FACTORIZATION BASED SPEECH STRATEGY IN COCHLEAR IMPLANTS

SPARSITY LEVEL IN A NON-NEGATIVE MATRIX FACTORIZATION BASED ...

引用

European Signal Processing Conference

作者： Hongmei Hu Nasser Mohammadiha Jalil Taghia Arne Leijon Mark E. Lutman Shouyan Wang Institute of Sound and Vibration Research University of Southampton School of Electrical Engineering Royal Institute of Technology

ISBN: (纸本)9781467310680

Non-negative matrix factorization (NMF) has increasingly been used as a tool in signal processing in the last years, but it has not been used in the cochlear implants (CIs). To improve the performance of CIs in noisy environments, a novel sparse strategy is proposed by applying NMF on envelopes of 22 channels. In the new algorithm, the noisy speech is first transferred to the time-frequency domain via a 22-channel filter bank and the envelope in each frequency channel is extracted;secondly, NMF is applied to the envelope matrix (envelopegram);finally, the sparsity condition is applied to the coefficient matrix to get more sparse representation. Speech reception threshold (SRT) subjective experiment was performed in combination with five objective measurements in order to choose the proper parameters for the sparse NMF model.

关键词： Non-negative matrix factorization Cochlear implants sparse coding Objective measurements Speech perception threshold matrix decomposition envelopes frequency channel NMF protocol Coefficient Matrix Speech speech reception threshold (SRT) indium Implants and Prostheses factorization Frequency-domain analysis ENVELOPE signal processing

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：