检索结果-内蒙古大学图书馆

International Conference on Computing and Network Communications

作者： Suchit Purohit Ronak Viroja Savita Gandhi Naina Chaudhary Department of Computer Science Gujarat University Ahmedabad India Tata Consultancy Services Pune India

ISBN: (纸本)9781467373104

Motivated from the need of automation of plant speciess recognition and availability of digital databases of plants,we propose an image based identification of speciess of plant. These images may belong to different organs of the plants such as leaf, stem or bark, flower and fruit. Different methods for recognition of the speciess are used according to the part of the plant to which the image belongs to. For flower category, fusion of shape, color and texture features are used. For other categories like stem, fruit, leaf and leafscan, sparsely coded SIFT features pooled with Spatial pyramid matching approach is used. To cater the seasonal and topographic influences on the appearance of the plant, our system also uses metadata i.e. content, date, time, latitude, longitude associated with images to aid the identification process and obtain more accurate results. For a given image of plant and associated metadata, the system recognizes the speciess of the given plant image and produces an output that contains the Family, Genus, and Speciess name. The proposed framework is implemented and tested on ImageClef data with 50 different classes of speciess. Maximum accuracy of 98% is attained in leaf scan sub-category whereas minimum accuracy is achieved in fruit sub-category which is 67.3 %.

关键词： SIFT sparse coding Plant Species Content based retrievel Spatial Pyramid matchin HSV color space Texture fetaures extraction

来源：评论

学校读者我要写书评

暂无评论

sparse coding of birdsong and receptive field structure in songbirds

引用

NETWORK-COMPUTATION IN NEURAL SYSTEMS 2009年第3期20卷 162-177页

作者： Greene, Garrett Barrett, David G. T. Sen, Kamal Houghton, Conor Trinity Coll Dublin Sch Math Dublin Ireland UCL Gatsby Computat Neurosci Unit London WC1E 6BT England Boston Univ Dept Biomed Engn Hearing Res Ctr Boston MA 02215 USA Boston Univ Dept Biomed Engn Ctr Biodynam Boston MA 02215 USA

Auditory neurons can be characterized by a spectro-temporal receptive field, the kernel of a linear filter model describing the neuronal response to a stimulus. With a view to better understanding the tuning properties of these cells, the receptive fields of neurons in the zebra finch auditory fore-brain are compared to a set of artificial kernels generated under the assumption of sparseness;that is, the assumption that in the sensory pathway only a small number of neurons need be highly active at any time. The sparse kernels are calculated by finding a sparse basis for a corpus of zebra-finch songs. This calculation is complicated by the highly-structured nature of the songs and requires regularization. The sparse kernels and the receptive fields, though differing in some respects, display several significant similarities, which are described by computing quantative properties such as the seperability index and Q-factor. By comparison, an identical calculation performed on human speech recordings yields a set of kernels which exhibit widely different tuning. These findings imply that Field L neurons are specifically adapted to sparsely encode birdsong and supports the idea that sparsification may be an important element of early sensory processing.

关键词： Auditory system natural scenes sparse coding spectro-temporal receptive field

来源：评论

学校读者我要写书评

暂无评论

REFINED CLOTHING TEXTURE PARSING BY EXPLOITING THE DISCRIMINATIVE MEANINGS OF sparse CODES

REFINED CLOTHING TEXTURE PARSING BY EXPLOITING THE DISCRIMIN...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Wang Fan Zhao Qiyang Yin Baolin Beihang Univ State Key Lab Software Dev Environm Beijing 100191 Peoples R China

ISBN: (纸本)9781479957514

Texture parsing benefits attribute-based clothing analysis and related applications, such as clothing retrieval and recognition. To deal with the large variations of clothing textures, in this paper, a new method is presented in which refined texture attributes are parsed. Based on the characteristics of clothing textures, refined texture attributes are proposed and parameterized. To estimate the attribute parameters, we exploit the discriminative meanings of sparse codes: the underlying connections between the attribute parameters and each component of sparse codes. The attribute parameters are mapped from the dominating components of sparse codes. Our experiments demonstrate the effectiveness of the proposed method.

关键词： sparse coding clothing texture attribute parsing

来源：评论

学校读者我要写书评

暂无评论

sparse representation for robust abnormality detection in crowded scenes

引用

PATTERN RECOGNITION 2014年第5期47卷 1791-1799页

作者： Zhu, Xiaobin Liu, Jing Wang, Jinqiao Li, Changsheng Lu, Hanqing Beijing Technol & Business Univ Sch Comp & Informat Engn Beijing 100048 Peoples R China Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing 100190 Peoples R China IBM Res China Beijing 100193 Peoples R China

In crowded scenes, the extracted low-level features, such as optical flow or spatio-temporal interest point, are inevitably noisy and uncertainty. In this paper, we propose a fully unsupervised non-negative sparse coding based approach for abnormality event detection in crowded scenes, which is specifically tailored to cope with feature noisy and uncertainty. The abnormality of query sample is decided by the sparse reconstruction cost from an atomically learned event dictionary, which forms a sparse coding bases. In our algorithm, we formulate the task of dictionary learning as a non-negative matrix factorization (NMF) problem with a sparsity constraint. We take the robust Earth Mover's Distance (EMD), instead of traditional Euclidean distance, as distance metric reconstruction cost function. To reduce the computation complexity of EMD, an approximate EMD, namely wavelet EMD, is introduced and well combined into our approach, without losing performance. In addition, the combination of wavelet EMD with our approach guarantees the convexity of optimization in dictionary learning. To handle both local abnormality detection (LAD) and global abnormality detection, we adopt two different types of spatio-temporal basis. Experiments conducted on four public available datasets demonstrate the promising performance of our work against the state-of-the-art methods. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： Nonnegative matrix factorization Crowded scene Abnormality detection sparse coding Earth mover's distance Wavelet EMD

来源：评论

学校读者我要写书评

暂无评论

Bilayer sparse Topic Model for Scene Analysis in Imbalanced Surveillance Videos

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2014年第12期23卷 5198-5208页

作者： Wang, Jinqiao Fu, Wei Lu, Hanqing Ma, Songde Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing 100190 Peoples R China China Elect Technol Grp Corp Res Inst 54 Shijiazhuang 050081 Peoples R China

Dynamic scene analysis has become a popular research area especially in video surveillance. The goal of this paper is to mine semantic motion patterns and detect abnormalities deviating from normal ones occurring in complex dynamic scenarios. To address this problem, we propose a data-driven and scene-independent approach, namely, Bilayer sparse topic model (BiSTM), where a given surveillance video is represented by a word-document hierarchical generative process. In this BiSTM, motion patterns are treated as latent topics sparsely distributed over low-level motion vectors, whereas a video clip can be sparsely reconstructed by a mixture of topics (motion pattern). In addition to capture the characteristic of extreme imbalance between numerous typical normal activities and few rare abnormalities in surveillance video data, a one-class constraint is directly imposed on the distribution of documents as a discriminant priori. By jointly learning topics and one-class document representation within a discriminative framework, the topic (pattern) space is more specific and explicit. An effective alternative iteration algorithm is presented for the model learning. Experimental results and comparisons on various public data sets demonstrate the promise of the proposed approach.

关键词： Dynamic scene analysis sparse coding topic model

来源：评论

学校读者我要写书评

暂无评论

Local identification of overcomplete dictionaries

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2015年第1期16卷

作者： Karin Schnass Department of Mathematics University of Innsbruck Innsbruck Austria

This paper presents the first theoretical results showing that stable identification of overcomplete µ-coherent dictionaries Φ ε Rd×K is locally possible from training signals with sparsity levels S up to the order O(µ-2) and signal to noise ratios up to O(√d). In particular the dictionary is recoverable as the local maximum of a new maximization criterion that generalizes the K-means criterion. For this maximization criterion results for asymptotic exact recovery for sparsity levels up to O(µ-1) and stable recovery for sparsity levels up to O(µ-2) as well as signal to noise ratios up to O(√d) are provided. These asymptotic results translate to finite sample size recovery results with high probability as long as the sample size N scales as O(K3dsε-2), where the recovery precision ε can go down to the asymptotically achievable precision. Further, to actually and the local maxima of the new criterion, a very simple Iterative Thresholding and K (signed) Means algorithm (ITKM), which has complexity O(dKN) in each iteration, is presented and its local efficiency is demonstrated in several experiments.

关键词： K-means dictionary identification dictionary learning finite sample size maximization criterion sample complexity sparse coding sparse component analysis sparse representation vector quantization

来源：评论

学校读者我要写书评

暂无评论

Continuous speech recognition with sparse coding

引用

COMPUTER SPEECH AND LANGUAGE 2009年第2期23卷 200-219页

作者： Smit, W. J. Barnard, E. Univ Pretoria ZA-0001 Pretoria South Africa Meraka Inst ZA-0001 Pretoria South Africa

sparse coding is an efficient way of coding information. In a sparse code most of the code elements are zero;very few are active. sparse codes are intended to correspond to the spike trains with which biological neurons communicate. In this article, we show how sparse codes can be used to do continuous speech recognition. We use the TIDIGITS dataset to illustrate the process. First a waveform is transformed into a spectrogram, and a sparse code for the spectrogram is found by means of a linear generative model. The spike train is classified by making use of a spike train model and dynamic programming. It is computationally expensive to find a sparse code. We use an iterative subset selection algorithm with quadratic programming for this process. This algorithm finds a sparse code in reasonable time if the input is limited to a fairly coarse spectral resolution. At this resolution, our system achieves a word error rate of 19%, whereas a system based on Hidden Markov Models achieves a word error rate of 15% at the same resolution. (C) 2008 Elsevier Ltd. All rights reserved.

关键词： sparse coding Spike train Speech recognition Linear generative model

来源：评论

学校读者我要写书评

暂无评论

OPTIMAL sparse APPROXIMATION WITH INTEGRATE AND FIRE NEURONS

引用

INTERNATIONAL JOURNAL OF NEURAL SYSTEMS 2014年第5期24卷 1440001-1440001页

作者： Shapero, Samuel Zhu, Mengchen Hasler, Jennifer Rozell, Christopher Georgia Tech Res Inst Elect Syst Lab Atlanta GA 30318 USA Georgia Inst Technol Atlanta GA 30332 USA Georgia Inst Technol Atlanta GA 30332 USA

sparse approximation is a hypothesized coding strategy where a population of sensory neurons (e. g. V1) encodes a stimulus using as few active neurons as possible. We present the Spiking LCA (locally competitive algorithm), a rate encoded Spiking Neural Network (SNN) of integrate and fire neurons that calculate sparse approximations. The Spiking LCA is designed to be equivalent to the nonspiking LCA, an analog dynamical system that converges on a l(1)-norm sparse approximations exponentially. We show that the firing rate of the Spiking LCA converges on the same solution as the analog LCA, with an error inversely proportional to the sampling time. We simulate in NEURON a network of 128 neuron pairs that encode 8x8 pixel image patches, demonstrating that the network converges to nearly optimal encodings within 20ms of biological time. We also show that when using more biophysically realistic parameters in the neurons, the gain function encourages additional l(0)-norm sparsity in the encoding, relative both to ideal neurons and digital solvers.

关键词： sparse coding spiking neural networks locally competitive algorithm

来源：评论

学校读者我要写书评

暂无评论

From Heuristic Optimization to Dictionary Learning: A Review and Comprehensive Comparison of Image Denoising Algorithms

引用

IEEE TRANSACTIONS ON CYBERNETICS 2014年第7期44卷 1001-1013页

作者： Shao, Ling Yan, Ruomei Li, Xuelong Liu, Yan Nanjing Univ Informat Sci & Technol Coll Elect & Informat Engn Nanjing 210044 Jiangsu Peoples R China Univ Sheffield Dept Elect & Elect Engn Sheffield S1 3JD S Yorkshire England Chinese Acad Sci Xian Inst Opt & Precis Mech State Key Lab Transient Opt & Photon Ctr OPT Imagery Anal & Learning Xian 710119 Peoples R China Hong Kong Polytech Univ Dept Comp Kowloon Hong Kong Peoples R China

Image denoising is a well explored topic in the field of image processing. In the past several decades, the progress made in image denoising has benefited from the improved modeling of natural images. In this paper, we introduce a new taxonomy based on image representations for a better understanding of state-of-the-art image denoising techniques. Within each category, several representative algorithms are selected for evaluation and comparison. The experimental results are discussed and analyzed to determine the overall advantages and disadvantages of each category. In general, the nonlocal methods within each category produce better denoising results than local ones. In addition, methods based on overcomplete representations using learned dictionaries perform better than others. The comprehensive study in this paper would serve as a good reference and stimulate new research ideas in image denoising.

关键词： Adaptive filters dictionary learning evaluation image denoising sparse coding spatial domain survey transform domain

来源：评论

学校读者我要写书评

暂无评论

Multiple Kernel sparse Representations for Supervised and Unsupervised Learning

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2014年第7期23卷 2905-2915页

作者： Thiagarajan, Jayaraman J. Ramamurthy, Karthikeyan Natesan Spanias, Andreas Arizona State Univ Sch Elect Comp & Energy Engn SenSIP Ctr Tempe AZ 85287 USA

In complex visual recognition tasks, it is typical to adopt multiple descriptors, which describe different aspects of the images, for obtaining an improved recognition performance. Descriptors that have diverse forms can be fused into a unified feature space in a principled manner using kernel methods. sparse models that generalize well to the test data can be learned in the unified kernel space, and appropriate constraints can be incorporated for application in supervised and unsupervised learning. In this paper, we propose to perform sparse coding and dictionary learning in the multiple kernel space, where the weights of the ensemble kernel are tuned based on graph-embedding principles such that class discrimination is maximized. In our proposed algorithm, dictionaries are inferred using multiple levels of 1D subspace clustering in the kernel space, and the sparse codes are obtained using a simple levelwise pursuit scheme. Empirical results for object recognition and image clustering show that our algorithm outperforms existing sparse coding based approaches, and compares favorably to other state-of-the-art methods.

关键词： sparse coding dictionary learning multiple kernel learning object recognition clustering

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：