2017 51st Asilomar Conference on Signals, Systems, and Computers最新文献_第9页

Partial differential equations for training deep neural networks 训练深度神经网络的偏微分方程

2017 51st Asilomar Conference on Signals, Systems, and Computers Pub Date : 2017-10-01 DOI: 10.1109/ACSSC.2017.8335634

P. Chaudhari, Adam M. Oberman, S. Osher, Stefano Soatto, G. Carlier

引用次数: 10

Frequency invariant beamforming for arbitrary planar arrays 任意平面阵列的频率不变波束形成

2017 51st Asilomar Conference on Signals, Systems, and Computers Pub Date : 2017-10-01 DOI: 10.1109/ACSSC.2017.8335527

A. Medda, Arjun Patel

引用次数: 1

Authentication of parties in piggy bank cryptography 小猪储蓄罐密码中各方的身份验证

2017 51st Asilomar Conference on Signals, Systems, and Computers Pub Date : 2017-10-01 DOI: 10.1109/ACSSC.2017.8335582

Prashanth Busireddygari, S. Kak

引用次数: 0

A best-features based digital rotoscope 一个最好的功能为基础的数字旋转镜

2017 51st Asilomar Conference on Signals, Systems, and Computers Pub Date : 2017-10-01 DOI: 10.1109/ACSSC.2017.8335175

Iain Murphy, T. Norlund, V. Pallipuram

{"title":"A best-features based digital rotoscope","authors":"Iain Murphy, T. Norlund, V. Pallipuram","doi":"10.1109/ACSSC.2017.8335175","DOIUrl":"https://doi.org/10.1109/ACSSC.2017.8335175","url":null,"abstract":"The paper presents a best-features based digital rotoscope to animate a video sequence. Our thesis is that corners in an image are viable feature points for animation because they move appreciably across frames. Our proposed rotoscope processes a video sequence one frame at a time and comprises four image processing stages namely, the background subtraction stage, two-phase Shi-Tomasi feature extraction stage, watershed segmentation stage, and the color palette stage. The background subtraction stage subtracts the background from the input image, thereby isolating the foreground colors and producing an inverted image. The two-phase Shi-Tomasi feature extraction stage performs two passes of corner detection on the inverted image to identify a user-defined number of best-features. The watershed segmentation stage uses the best-features as markers to segment the input frame. Finally, the color palette stage colors each one of the segments with the average of the input frame's color values in that segment, thereby creating a rotoscoped frame. After processing all of the frames in a video sequence, the digital rotoscope produces an animated movie. We study the impact of choosing different numbers of best-features on the quality of animation. Our empirical study reveals that for a frame-size of 480 × 640 × 3, 1000 features or more produce effective animation. Our four-stage digital rotoscope provides opportunities for parallel implementations on high-performance architectures, thereby creating avenues for fast analysis.","PeriodicalId":296208,"journal":{"name":"2017 51st Asilomar Conference on Signals, Systems, and Computers","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123443630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Dimension spreading for coherent opportunistic communications 连贯机会通信的维度扩展

2017 51st Asilomar Conference on Signals, Systems, and Computers Pub Date : 2017-10-01 DOI: 10.1109/ACSSC.2017.8335703

Jordi Borras, Josep Font-Segura, J. Riba, G. Vázquez

引用次数: 7

On noise reduction for handwritten writer identification 手写体识别中的降噪研究

2017 51st Asilomar Conference on Signals, Systems, and Computers Pub Date : 2017-10-01 DOI: 10.1109/ACSSC.2017.8335714

Karl S. Ni, P. Callier, B. Hatch, Jonathan Mastarone, James Cline

{"title":"On noise reduction for handwritten writer identification","authors":"Karl S. Ni, P. Callier, B. Hatch, Jonathan Mastarone, James Cline","doi":"10.1109/ACSSC.2017.8335714","DOIUrl":"https://doi.org/10.1109/ACSSC.2017.8335714","url":null,"abstract":"Academic work in identifying writers of handwritten documents has previously focused on clean benchmark datasets: plain white documents with uniform writing instruments. Solutions on this type of data have achieved hit-in-top-10 accuracy rates reaching upwards of 98%. Unfortunately, transferring competitive techniques to handwritten documents with noise is nontrivial, where performance drops by two-thirds. Noise in the context of handwritten documents can manifest itself in many ways, from irrelevant structured additions, e.g., graph paper, to unstructured partial occlusion, e.g. coffee stains and stamps. Additional issues that confound algorithmic writer identification solutions include the use of different writing implement, age, and writing state of mind. The proposed work explores training denoising neural networks to aid in identifying authors of handwritten documents. Our algorithms are trained on existing clean datasets artificially augmented with noise, and we evaluate them on a commissioned dataset, which features a diverse but balanced set of writers, writing implements, and writing substrates (incorporating various types of noise). Using the proposed denoising algorithm, we exceed the state of the art in writer identification of noisy handwritten documents by a significant margin.","PeriodicalId":296208,"journal":{"name":"2017 51st Asilomar Conference on Signals, Systems, and Computers","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121587288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Consensus state gram matrix estimation for stochastic switching networks from spectral distribution moments 基于谱分布矩的随机交换网络一致状态克阵估计

2017 51st Asilomar Conference on Signals, Systems, and Computers Pub Date : 2017-10-01 DOI: 10.1109/ACSSC.2017.8335596

Stephen Kruzick, José M. F. Moura

{"title":"Consensus state gram matrix estimation for stochastic switching networks from spectral distribution moments","authors":"Stephen Kruzick, José M. F. Moura","doi":"10.1109/ACSSC.2017.8335596","DOIUrl":"https://doi.org/10.1109/ACSSC.2017.8335596","url":null,"abstract":"Reaching distributed average consensus quickly and accurately over a network through iterative dynamics represents an important task in numerous distributed applications. Suitably designed filters applied to the state values can significantly improve the convergence rate. For constant networks, these filters can be viewed in terms of graph signal processing as polynomials in a single matrix, the consensus iteration matrix, with filter response evaluated at its eigenvalues. For random, time-varying networks, filter design becomes more complicated, involving eigendecompositions of sums and products of random, time-varying iteration matrices. This paper focuses on deriving an estimate for the Gram matrix of error in the state vectors over a filtering window for large-scale, stationary, switching random networks. The result depends on the moments of the empirical spectral distribution, which can be estimated through Monte-Carlo simulation. This work then defines a quadratic objective function to minimize the expected consensus estimate error norm. Simulation results provide support for the approximation.","PeriodicalId":296208,"journal":{"name":"2017 51st Asilomar Conference on Signals, Systems, and Computers","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122847535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Zero-forcing precoding using generalized inverses for G.fast DSL systems 基于广义逆的G.fast DSL系统强制零预编码

2017 51st Asilomar Conference on Signals, Systems, and Computers Pub Date : 2017-10-01 DOI: 10.1109/ACSSC.2017.8335652

Andreas Barthelme, M. Joham, Rainer Strobel, W. Utschick

引用次数: 1

Active spectrum sensing with sequential sub-Nyquist sampling 主动频谱传感与顺序亚奈奎斯特采样

2017 51st Asilomar Conference on Signals, Systems, and Computers Pub Date : 2017-10-01 DOI: 10.1109/ACSSC.2017.8335400

Lorenzo Ferrari, A. Scaglione

引用次数: 0

Beyond consensus and synchrony in decentralized online optimization using saddle point method 鞍点法在分散在线优化中的超越共识与同步

2017 51st Asilomar Conference on Signals, Systems, and Computers Pub Date : 2017-10-01 DOI: 10.1109/ACSSC.2017.8335186

A. S. Bedi, Alec Koppel, K. Rajawat

{"title":"Beyond consensus and synchrony in decentralized online optimization using saddle point method","authors":"A. S. Bedi, Alec Koppel, K. Rajawat","doi":"10.1109/ACSSC.2017.8335186","DOIUrl":"https://doi.org/10.1109/ACSSC.2017.8335186","url":null,"abstract":"We consider online learning problems in multiagent systems comprised of distinct subsets of agents operating without a common time-scale. Each individual in the network is charged with minimizing the global regret, which is a sum of the instantaneous sub-optimality of each agent's actions with respect to a fixed global clairvoyant actor with access to all costs across the network for all time up to a time-horizon T. Since agents are not assumed to be of the same type, the hypothesis that all agents seek a common action is violated, and thus we instead introduce a notion of network discrepancy as a measure of how well agents coordinate their behavior while retaining distinct local behavior. Moreover, agents are not assumed to receive the sequentially arriving costs on a common time index, and thus seek to learn in an asynchronous manner. A variant of the Arrow-Hurwicz saddle point algorithm is proposed to control the growth of global regret and network discrepancy. This algorithm uses Lagrange multipliers to penalize the discrepancies between agents and leads to an implementation that relies on local operations and exchange of variables between neighbors. Decisions made with this method lead to regret whose order is O(√T) and network discrepancy O(T3/4). Empirical evaluation is conducted on an asynchronously operating sensor network estimating a spatially correlated random field.","PeriodicalId":296208,"journal":{"name":"2017 51st Asilomar Conference on Signals, Systems, and Computers","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130184605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7