检索结果-内蒙古大学图书馆

Color video denoising using epitome and sparse coding

EXPERT SYSTEMS WITH APPLICATIONS 2015年第2期42卷 751-759页

作者： Lee, Hwea Yee Hoo, Wai Lam Chan, Chee Seng Univ Malaya Ctr Image & Signal Proc Fac Comp Sci & Informat Technol Kuala Lumpur 50603 Malaysia

Denoising is a process that remove noise from a signal. In this paper, we present a unified framework to deal with video denoising problems by adopting a two-steps process, namely the video epitome and sparse coding. First, the video epitome will summarize the video contents and remove the redundancy information to generate a single compact representation to describe the video content. Second, employing the single compact representation as an input, the sparse coding will generate a visual dictionary for the video sequence by estimating the most representative basis elements. The fusion of these two methods have resulted an enhanced, compact representation for the denoising task. Experiments on the publicly available datasets have shown the effectiveness of our proposed system in comparison to the state-of-the-art algorithms in the video denoising task. (C) 2014 Elsevier Ltd. All rights reserved.

关键词： Video denoising Video epitome sparse coding

来源：评论

学校读者我要写书评

暂无评论

Exploitation of image statistics with sparse coding in the case of stereo vision

引用

NEURAL NETWORKS 2021年 135卷 158-176页

作者： Ecke, Gerrit A. Papp, Harald M. Mallot, Hanspeter A. Univ Tubingen Dept Biol Cognit Neurosci Unit Morgenstelle 28 D-72076 Tubingen Germany Mercedes Benz AG Leibnizstr 2 D-71032 Boblingen Germany

The sparse coding algorithm has served as a model for early processing in mammalian vision. It has been assumed that the brain uses sparse coding to exploit statistical properties of the sensory stream. We hypothesize that sparse coding discovers patterns from the data set, which can be used to estimate a set of stimulus parameters by simple readout. In this study, we chose a model of stereo vision to test our hypothesis. We used the Locally Competitive Algorithm (LCA), followed by a naive Bayes classifier, to infer stereo disparity. From the results we report three observations. First, disparity inference was successful with this naturalistic processing pipeline. Second, an expanded, highly redundant representation is required to robustly identify the input patterns. Third, the inference error can be predicted from the number of active coefficients in the LCA representation. We conclude that sparse coding can generate a suitable general representation for subsequent inference tasks. (c) 2020 Published by Elsevier Ltd.

关键词： sparse coding Locally Competitive Algorithm (LCA) Efficient coding Compact code Probabilistic inference Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate sparse coding of Visual Stimuli With a Simple, Ultralow-Energy Spiking Architecture

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2019年第7期30卷 2173-2187页

作者： Woods, Walt Teuscher, Christof Portland State Univ Dept Elect & Comp Engn Portland OR 97207 USA

Memristive crossbars have become a popular means for realizing unsupervised and supervised learning techniques. In previous neuromorphic architectures with leaky integrate-and-fire neurons, the crossbar itself has been separated from the neuron capacitors to preserve mathematical rigor. In this paper, we sought to design a simplified sparse coding circuit without this restriction, resulting in a fast circuit that approximated a sparse coding operation at a minimal loss in accuracy. We showed that connecting the neurons directly to the crossbar resulted in a more energy-efficient sparse coding architecture and alleviated the need to prenormalize receptive fields. This paper provides derivations for the design of such a network, named the simple spiking locally competitive algorithm, as well as CMOS designs and results on the CIFAR and MNIST data sets. Compared to a nonspiking, nonapproximate model which scored 33% on CIFAR-10 with a single-layer classifier, this hardware scored 32% accuracy. When used with a state-of-the-art deep learning classifier, the nonspiking model achieved 82% and our simplified, spiking model achieved 80% while compressing the input data by 92%. Compared to a previously proposed spiking model, our proposed hardware consumed 99% less energy to do the same work at 21x the throughput. Accuracy held out with online learning to a write variance of 3%, suitable for the often reported 4-bit resolution required for neuromorphic algorithms, with offline learning to a write variance of 27%, and with read variance to 40%. The proposed architecture's excellent accuracy, throughput, and significantly lower energy usage demonstrate the utility of our innovations.

关键词： Locally competitive algorithm (LCA) memristors neuromorphic architecture sparse coding spiking architecture

来源：评论

学校读者我要写书评

暂无评论

Detection of seagrass scars using sparse coding and morphological filter

引用

REMOTE SENSING OF ENVIRONMENT 2018年 213卷 92-103页

作者： Oguslu, E. Islam, Kazi Perez, Daniel Hill, V. J. Bissett, W. P. Zimmerman, R. C. Li, J. Turkish Air Force NCO Vocat Coll Dept Elect & Commun Izmir Turkey Old Dominion Univ Dept Ocean Earth & Atmospher Sci Norfolk VA 23529 USA Florida Environm Res Inst Tampa FL 33611 USA Old Dominion Univ Dept Modelling Simulat & Visualizat Engn Norfolk VA 23529 USA Old Dominion Univ Dept Elect & Comp Engn Norfolk VA 23529 USA

The proximity of seagrass meadows to centers of human activity makes them vulnerable to a variety of habitat degrading insults. Physical scarring has long been recognized as an important but difficult-to-quantify source of habitat fragmentation and seagrass loss. We present a pixel-based algorithm to detect seafloor propeller seagrass scars in shallow water that promises to automate the detection and measurement of scars across the submarine landscape. (1)We applied the algorithm to multispectral and panchromatic images captured at the Deckle Beach, Florida using the WorldView-2 commercial satellite. The algorithm involves four steps using spectral and spatial information from radiometrically calibrated multispectral and panchromatic images. First, we fused multispectral and panchromatic images using a principal component analysis (PCA)-based pan-sharpening method to obtain multispectral pan-sharpened bands. In the second step, we enhanced the image contrast of the pan-sharpened bands for better scar detection. In the third step, we classified the contrast enhanced image pixels into scar and non-scar categories based on a sparse coding algorithm that produced an initial scar map in which false positive scar pixels were also present. In the fourth step, we applied post-processing techniques including a morphological filter and local orientation to reduce false positives. Our results show that the proposed method may be implemented on a regular basis to monitor changes in habitat characteristics of coastal waters.

关键词： Remote sensing sparse coding Seagrass scar detection

来源：评论

学校读者我要写书评

暂无评论

sparse coding based on L2,1-norm and manifold regularization for remote sensing images 12

Sparse coding based on L2,1-norm and manifold regularization...

引用

12th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)

作者： Yuan Jianjun Li Shifeng Southwest Univ Coll Artificial Intelligence Chongqing Peoples R China Chongqing Geomat & Remote Sensing Ctr Geomat & Remote Sensing Ctr Chongqing Peoples R China

ISBN: (纸本)9798350331547

sparse coding is an important tool in image re-construction. In this paper, a novel sparse coding algorithm based on L2,1-norm and manifold regularization is developed to reconstruct remote sensing images. In the proposed algorithm, loss function based on L2,1-norm has the capability of reducing outliers. Dictionary and sparse coding based on L2,1-norm can select features with joint sparsity. Manifold regularization can retain more geometric information. An efficient algorithm for updating dictionary is developed, and the convergence is proved. To this end, we compare the proposed algorithm with other existing methods. Experiments on real remote sensing images demonstrate that the proposed algorithm has promising reconstruction results.

关键词： sparse coding dictionary learning manifold regularization remote sensing image reconstruction

来源：评论

学校读者我要写书评

暂无评论

sparse coding on Multiple Manifold Data 21

引用

21st International Conference on Neural Information Processing (ICONIP)

作者： Zhang, Hanchao Xu, Jinhua East China Normal Univ Dept Comp Sci & Technol Shanghai Peoples R China

ISBN: (纸本)9783319126401

sparse coding has been widely used in computer vision. While capturing high-level semantics, the independent coding process neglects connections between data points. Some recent methods use Laplacian matrix to learn sparse representations with locality preserving on the manifold. Considering data points may lie in or close to multiple low dimensional manifolds embedded in the high dimensional descriptor space, we use sparse representations to code the local similarity between data points on each manifold and embed this topology to sparse coding algorithm. By keeping the locality of manifolds we can preserve the similarity and separability at the same time. Experimental results on several benchmark data sets show our algorithm is effective.

关键词： sparse coding sparse representation manifold learning Laplacian matrix locality preserving

来源：评论

学校读者我要写书评

暂无评论

On robust face recognition via sparse coding: the good, the bad and the ugly

引用

IET BIOMETRICS 2014年第4期3卷 176-189页

作者： Wong, Yongkang Harandi, Mehrtash T. Sanderson, Conrad Natl Univ Singapore SeSaMe Ctr Singapore 117548 Singapore Univ Queensland Sch ITEE Brisbane Qld 4072 Australia NICTA Canberra ACT 2601 Australia Australian Natl Univ Canberra ACT 0200 Australia Queensland Univ Technol Brisbane Qld 4000 Australia

In the field of face recognition, sparse representation (SR) has received considerable attention during the past few years, with a focus on holistic descriptors in closed-set identification applications. The underlying assumption in such SR-based methods is that each class in the gallery has sufficient samples and the query lies on the subspace spanned by the gallery of the same class. Unfortunately, such an assumption is easily violated in the face verification scenario, where the task is to determine if two faces (where one or both have not been seen before) belong to the same person. In this study, the authors propose an alternative approach to SR-based face verification, where SR encoding is performed on local image patches rather than the entire face. The obtained sparse signals are pooled via averaging to form multiple region descriptors, which then form an overall face descriptor. Owing to the deliberate loss of spatial relations within each region (caused by averaging), the resulting descriptor is robust to misalignment and various image deformations. Within the proposed framework, they evaluate several SR encoding techniques: l(1)-minimisation, sparse Autoencoder Neural Network (SANN) and an implicit probabilistic technique based on Gaussian mixture models. Thorough experiments on AR, FERET, exYaleB, BANCA and ChokePoint datasets show that the local SR approach obtains considerably better and more robust performance than several previous state-of-the-art holistic SR methods, on both the traditional closed-set identification task and the more applicable face verification task. The experiments also show that l(1)-minimisation-based encoding has a considerably higher computational cost when compared with SANN-based and probabilistic encoding, but leads to higher recognition rates.

关键词： face recognition Gaussian processes image coding minimisation neural nets visual databases local SR approach AR datasets FERET datasets exYaleB datasets BANCA datasets ChokePoint datasets Gaussian mixture models implicit probabilistic technique SANN sparse autoencoder neural network l1-minimisation image deformations spatial relations multiple region descriptors sparse signals local image patches SR encoding face verification scenario closed-set identification applications holistic descriptors sparse representation sparse coding robust face recognition

来源：评论

学校读者我要写书评

暂无评论

A sparse coding approach for local-to-global 3D shape description

引用

VISUAL COMPUTER 2014年第11期30卷 1233-1245页

作者： Boscaini, Davide Castellani, Umberto Univ Lugano Lugano Switzerland Univ Verona Dept Comp Sci I-37100 Verona Italy LASMEA Lab Clermont Ferrand France

The definition of reliable shape descriptors is an essential topic for 3D object retrieval. In general, two main approaches are considered: global, and local. Global approaches are effective in describing the whole object, while local ones are more suitable to characterize small parts of the shape. Recently some strategies to combine these two approaches have been proposed which are mainly concentrated to the so-called bag of words paradigm. With this paper we address this problem and propose an alternative strategy that goes beyond the bag of word approach. In particular, a sparse coding technique is exploited for the 3D domain: a set of local shape descriptors are collected from the shape, and then a dictionary is trained as generative model. In this fashion the dictionary is used as global shape descriptor for shape retrieval purposes. Several experiments are performed on standard databases in order to evaluate the proposed method in challenging situations like the case of 'SHREC 2011: robustness benchmark' where strong shape transformations are included, and the case of 'SHREC 2007: partial matching track' where composite models are considered in the query phase. A drastic improvement of the proposed method is observed by showing that sparse coding approach is particularly suitable for local-to-global description and outperforms other approaches such as the bag of words.

关键词： 3D object retrieval sparse coding Bag of words Partial shape matching

来源：评论

学校读者我要写书评

暂无评论

An Accurate and Efficient Device-Free Localization Approach Based on sparse coding in Subspace

引用

IEEE ACCESS 2018年 6卷 61782-61799页

作者： Huang, Huakun Zhao, Haoli Li, Xiang Ding, Shuxue Zhao, Lingjun Li, Zhenni Univ Aizu Sch Comp Sci & Engn Aizu Wakamatsu Fukushima 9650005 Japan Guangdong Univ Technol Sch Automat Guangdong Key Lab IoT Informat Technol Guangzhou 510006 Guangdong Peoples R China

In practical device-free localization (DFL) applications, for enlarging the monitoring area and improving localization accuracy, too many nodes need to be deployed, which results in a large volume of DFL data with high dimensions. This arises a key problem of seeking an accurate and efficient approach for DFL. In order to address this problem, this paper regards DFL as a problem of sparse-representation-based classification;builds a sparse model;and then proposes two sparse-coding-based algorithms. The first algorithm, sparse coding via the iterative shrinkage-thresholding algorithm (SC-ISTA), is efficient for handling high-dimensional data. And then, subspace techniques are further utilized, followed by performing sparse coding in the low-dimensional signal subspace, which leads to the second algorithm termed subspace-based SC-ISTA (SSC-ISTA). Experiments with the real-world data set are conducted for single-target and multi-target localization, and three typical machine learning algorithms, deep learning based on autoencoder, K-nearest neighbor, and orthogonal matching pursuit, are compared. Experimental results show that both SC-ISTA and SSC-ISTA can achieve high localization accuracies of 100% and are robust to noisy data when SNR is greater than 10 dB, and the time costs for sparse coding of SC-ISTA and SSC-ISTA are 2.1 x 10(-3) s and 2.1 x 10(-4) s respectively, which indicates that the proposed algorithms outperform the other three ones.

关键词： Device-free localization wireless sensor networks multi-targets sparse coding subspace iterative shrinkage-thresholding algorithm

来源：评论

学校读者我要写书评

暂无评论

Multi-information fusion sparse coding with preserving local structure for hyperspectral image classification

引用

JOURNAL OF APPLIED REMOTE SENSING 2017年第4期11卷

作者： Wei, Xiaohui Zhu, Wen Liao, Bo Gu, Changlong Li, Weibiao Hunan Univ Coll Informat Sci & Engn Changsha Hunan Peoples R China

The key question of sparse coding (SC) is how to exploit the information that already exists to acquire the robust sparse representations (SRs) of distinguishing different objects for hyperspectral image (HSI) classification. We propose a multi-information fusion SC framework, which fuses the spectral, spatial, and label information in the same level, to solve the above question. In particular, pixels from disjointed spatial clusters, which are obtained by cutting the given HSI in space, are individually and sparsely encoded. Then, due to the importance of spatial structure, graph-and hypergraph-based regularizers are enforced to motivate the obtained representations smoothness and to preserve the local consistency for each spatial cluster. The latter simultaneously considers the spectrum, spatial, and label information of multiple pixels that have a great probability with the same label. Finally, a linear support vector machine is selected as the final classifier with the learned SRs as input. Experiments conducted on three frequently used real HSIs show that our methods can achieve satisfactory results compared with other state-of-the-art methods. (C) 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)

关键词： hyperspectral image classification multi-information fusion sparse coding hyper-Laplacian parallel sparse recovery support vector machine

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：