检索结果-内蒙古大学图书馆

Application of the method of pyramid for synthesis of parallel algorithm for difference solution of the two-dimensional partial differentials equation

Application of the method of pyramid for synthesis of parall...

引用

2016 International Conference Information Technology and Nanotechnology, ITNT 2016

作者： Golovashkin, D.L. Yablokova, L.v. Belova, E.v. Samara National Research University Samara Russia Image Processing Systems Institute Branch of the Federal Scientific Research Centre Crystallography and Photonics Russian Academy of Sciences Samara Russia

The work is devoted to the synthesis and investigation of parallel algorithm for a finite difference solution of the Poisson equation using the Jacobi method. For example, two-dimensional case demonstrates the efficac... 详细信息

关键词： Parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Medical image segmentation using object shape models: A critical review on recent trends, and alternative directions 5th

Medical image segmentation using object shape models: A crit...

引用

5th Eccomas Thematic Conference on Computational vision and Medical image processing, vipimage 2015

作者： Falcão, Alexandre Xavier Spina, Thiago vallin Martins, Samuel Botter Phellan, Renzo Institute of Computing University of Campinas Campinas Brazil Eldorado Research Institute Campinas Brazil

ISBN: (纸本)9781138029262

Segmentation is important to define the spatial extension of body anatomic structures (objects) in medical images for quantitative analysis. In this context, it is desirable to eliminate (at least minimize) user interaction. This aim is feasible by combining object delineation algorithms with Object Shape Models (OSMs). While the former can better capture the actual shape of the object in the image, the latter provides shape constraints to assist its location and delineation. We review two important classes of OSMs for medical image segmentation: Statistical (SOSMs) and Fuzzy (FOSMs). SOSMs rely on the image mapping onto a reference coordinate system, which indicates the probability of each voxel to be in the object (a probabilistic atlas built from a set of training images and their segmentation masks). Imperfect mappings due to shape and texture variations asks for object delineation algorithms, but the methods usually assume that the atlas is at the best position for delineation. Multiple atlases per object can mitigate the problem and a recent trend is to use each training mask as an individual atlas. By mapping them onto the coordinate system of a new image, object delineation can be accomplished by label fusion. However, the processing time for deformable registration is critical to make SOSMs suitable for large scale studies. FOSMs appear as a recent alternative to avoid reference systems (deformable registration) by translating the training masks to a common reference point for model construction. This relaxes the shape constraints, but asks for a more effective object delineation algorithm and some efficient approach for object’s location. One of the solutions, named optimum object search, translates the model inside an estimated search region in the image while a criterion function guides translation and determines the best delineated object among candidates. This makes segmentation with FOSMs considerably faster than with SOSMs, but SOSMs that adopt the o

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Predicting learners' multi-question performance based on neural networks 4

Predicting learners' multi-question performance based on neu...

引用

4th International Conference on Behavioral, Economic, and Socio-Cultural Computing, BESC 2017

作者： Liao, Pan Sun, Yuan Ye, Shiwei Li, Xin Su, Guiping Sun, Yi School of Computer and Control Engineering University of Chinese Academy of Sciences China Information and Society Research Division National Institute of Informatics Tokyo Japan Big Data Research Institute Hefei China

ISBN: (纸本)9781538623657

As massive open online courses (MOOCs) and online intelligent tutoring systems(ITS) have become increasingly widespread, the number of learners enrolled in online courses has shown explosive growth. However, these learners are likely to have acquired knowledge from diverse educational and vocational backgrounds. Therefore, it is unwise to apply the same criteria and assessment questions to assess all learners' abilities without differentiation. Therefore, the demand for the adaptive arrangement of questions for online learners is ever critical. Deep learning is a new increasingly popular approach for handling extraordinarily complex problems such as image recognition and natural language processing. In this research, we use neural networks to forecast learners' multi-question performance on new test questions and propose a new concept called predictable property for the first time to explain the reasons why neural networks can be applied to predict learners' multi-question performance based on their previous question responses. This approach means that fewer questions need to be answered by learners although more information can be gathered about them through the use of deep-learning-based techniques. Finally, we use both artificial datasets generated by cognitive models and three real-world datasets to validate the algorithm's performance. Experiments show a promising research result when using deep learning to predict learner performance in multi-question tasks and can ultimately provide more accurate adaptive tests for learners. © 2017 IEEE.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

Significance of Feature Selection for image Steganalysis 1

Significance of Feature Selection for Image Steganalysis

引用

1st IEEE International Conference on Computational systems and Information Technology for Sustainable Solutions (CSITSS)

作者： Chhikara, Rita Rana Kumari, Meena NorthCap Univ Dept CSE IT Guragon India

ISBN: (纸本)9781509010226

Steganalysis is capable of identifying the carrier(s) which have information hidden in them in such a way that their very existence is concealed. In this paper we propose a classification system with neural networks which reduces computational complexity through a pre-processing step (feature selection) performed by Bhattacharyya distance for image steganalysis. This approach is able to identify relevant features which are a subset of original features extracted from spatial as well as transform domain. It helps in overcoming the problem of "curse of dimensionalty" by removing redundant features by feature selection step before classifying the dataset. The experiments are performed on dataset obtained by four steganography algorithms outguess, steghide, PQ and nsF5 with two classifiers Support vector Machine and Back Propagation neural networks. Classifier in combination with Bhattacharyya distance filter feature selection approach shows an improvement of 2-20% against total number of features.

关键词： Steganography Steganalysis Bhattacharyya Distance Neural Networks

来源：评论

学校读者我要写书评

暂无评论

A Graph Matching Algorithm for User Authentication in Data Networks using image-based Physical Unclonable Functions

A Graph Matching Algorithm for User Authentication in Data N...

引用

Computing Conference

作者： Ali valehi Abolfazl Razi Bertrand Cambou Weijie Yu Michael Kozicki School of Informatics Computing and Cyber Security (SICCS) Northern Arizona University School of Electrical Computing and Energy Engineering (ECEE) Arizona State University

ISBN: (纸本)9781509054442

Recently, Physically Unclonable Functions (PUFs) received considerable attention in order to developing security mechanisms for applications such as Internet of Things (IoT) by exploiting the natural randomness in device-specific characteristics. This approach complements and improves the conventional security algorithms that are vulnerable to security attacks due to recent advances in computational technology and fully automated hacking systems. In this project, we propose a new authentication mechanism based on a specific implementation of PUF using metallic dendrites. Dendrites are nanomaterial devices that contain unique, complex and unclonable patterns (similar to human DNAs). We propose a method to process dendrite images. The proposed framework comprises several steps including denoising, skeletonizing, pruning and feature points extraction. The feature points are represented in terms of a tree-based weighted algorithm that converts the authentication problem to a graph matching problem. The test object is compared against a database of valid patterns using a novel algorithm to perform user identification and authentication. The proposed method demonstrates a high level of accuracy and a low computational complexity that grows linearly with the number of extracted points and database size. It also significantly reduces the required in-network storage capacity and communication rates to maintain database of users in large-scale networks.

关键词： Information-Security image-processing Graph-Matching Authentication

来源：评论

学校读者我要写书评

暂无评论

video inpainting of complex scenes based on local statistical model 14

Video inpainting of complex scenes based on local statistica...

引用

image processing: algorithms and systems XIv 2016

作者： voronin, v.v. Sizyakin, R.A. Marchuk, v.I. Cen, Yigang Galustov, G.G. Egiazarian, K.O. Don State Technical university Dept. of Radio-Electronics Systems Gagarina 1 Rostov on Don Russia Institute of Information Science Beijing Jiaotong University Beijing China Southern Federal University Nekrasovski 44 Taganrog Russia Dept. of Signal Processing Tampere University of Technology Korkeakoulunkatu 1 TampereFI-33720 Finland

This paper describes a framework for temporally consistent video completion. Proposed method allow to remove dynamic objects or restore missing or tainted regions present in a video sequence by utilizing spatial and temporal information from neighboring scenes. The algorithm iteratively performs following operations: achieve frame;update the scene model;update positions of moving objects;finding a set of descriptors that encapsulate the information necessary to reconstruct a frame;replace parts of the frame occupied by the objects marked for remove with use of a 3D patches. In this paper, we extend an image inpainting algorithm based texture and structure reconstruction by incorporating an improved strategy for video. Our algorithm is able to deal with a variety of challenging situations which naturally arise in video inpainting, such as the correct reconstruction of dynamic textures, multiple moving objects and moving background. Experimental comparisons to state-of-the-art video completion methods demonstrate the effectiveness of the proposed approach. © 2016 Society for Imaging Science and Technology.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Deep Belief Network Based Part-of-Speech Tagger for Telugu Language 2nd

Deep Belief Network Based Part-of-Speech Tagger for Telugu L...

引用

2nd International Conference on Computer and Communication Technologies

作者： Jagadeesh, M. Kumar, M. Anand Soman, K. P. Atlas Healthcare Software India Pvt Coimbatore Tamil Nadu India Amrita Vishwa Vidyapeetham Ctr Excellence Computat Engn & Networking Coimbatore Tamil Nadu India

ISBN: (纸本)9788132225263;9788132225256

Indian languages have very less linguistic resources, though they have a large speaker base. They are very rich in morphology, making it very difficult to do sequential tagging or any type of language analysis. In natural language processing, parts-of-speech (POS) tagging is the basic tool with which it is possible to extract terminology using linguistic patterns. The main aim of this research is to do sequential tagging for Indian languages based on the unsupervised features and distributional information of a word with its neighboring words. The results of the machine learning algorithms depend on the data representation. Not all the data contribute to creation of the model, leading a few in vain and it depends on the descriptive factors of data disparity. Data representations are designed by using domain-specific knowledge but the aim of Artificial Intelligence is to reduce these domain-dependent representations, so that it can be applied to the domains which are new to one. Recently, deep learning algorithms have acquired a substantial interest in reducing the dimension of features or extracting the latent features. Recent development and applications of deep learning algorithms are giving impressive results in several areas mostly in image and text applications.

关键词： Natural language processing Deep belief networks Restricted Boltzmann machine Neural networks POS tagging

来源：评论

学校读者我要写书评

暂无评论

Information Theory-based Detection of Noisy Bit Planes in Medical images 29

Information Theory-based Detection of Noisy Bit Planes in Me...

引用

29th SIBGRAPI Conference on Graphics, Patterns and images (SIBGRAPI)

作者： de Oliveira, Hugo N. dos Santos, Jefersson A. de Melo, Matheus C. do Rego, Thais G. Batista, Leonardo v. Univ Fed Minas Gerais Dept Ciencia Computacao Belo Horizonte MG Brazil Univ Fed Paraiba UFPB Ctr Informat Joao Pessoa Paraiba Brazil

ISBN: (纸本)9781509035687

Mammographic Computer-Aided Diagnosis systems are applications designed to assist radiologists in diagnosis of malignancy in mammographic findings. Most methods described in the literature do not perform a proper preprocessing step in mammographic images prior to classification, which can generate inconsistent results due to the potentially large amount of noise in medical images. This paper proposes a new method based on Information Theory and Data Compression for detection of random noise in image bit planes. In order to validate the efficiency of the proposed noise removal method, we used Machine Learning algorithms to classify mammographic findings from the Digital Database for Screening Mammography. Results using texture features indicate that a reduction in the radiometric resolution of 4 or 5 bit planes in digitized screen film mammographic images result in a better classification performance.

关键词： noise detection mammogram classification information theory data compression

来源：评论

学校读者我要写书评

暂无评论

Bio-inspired computer vision: Towards a synergistic approach of artificial and biological vision

引用

COMPUTER vISION AND image UNDERSTANDING 2016年 150卷 1-30页

作者： Medathati, N. v. Kartheek Neumann, Heiko Masson, Guillaume S. Kornprobst, Pierre Inria Sophia Antipolis Mediterranee Biovis Team 2004 Route LuciolesBP 93 F-06902 Sophia Antipolis France Univ Ulm Inst Neural Informat Proc D-89081 Ulm Germany CNRS UMR7289 Inst Neurosci Timone 27 Blvd Jean Moulin F-13005 Marseille France Aix Marseille Univ 27 Blvd Jean Moulin F-13005 Marseille France

Studies in biological vision have always been a great source of inspiration for design of computer vision algorithms. In the past, several successful methods were designed with varying degrees of correspondence with biological vision studies, ranging from purely functional inspiration to methods that utilise models that were primarily developed for explaining biological observations. Even though it seems well recognised that computational models of biological vision can help in design of computer vision algorithms, it is a non-trivial exercise for a computer vision researcher to mine relevant information from biological vision literature as very few studies in biology are organised at a task level. In this paper we aim to bridge this gap by providing a computer vision task centric presentation of models primarily originating in biological vision studies. Not only do we revisit some of the main features of biological vision and discuss the foundations of existing computational studies modelling biological vision, but also we consider three classical computer vision tasks from a biological perspective: image sensing, segmentation and optical flow. Using this task-centric approach, we discuss well-known biological functional principles and compare them with approaches taken by computer vision. Based on this comparative analysis of computer and biological vision, we present some recent models in biological vision and highlight a few models that we think are promising for future investigations in computer vision. To this extent, this paper provides new insights and a starting point for investigators interested in the design of biology-based computer vision algorithms and pave a way for much needed interaction between the two communities leading to the development of synergistic models of artificial and biological vision. (C) 2016 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY license.

关键词： Canonical computations Event based processing Dynamic sensors Multiplexed representation Population coding Soft selectivity Feedback Lateral interactions Form-motion interactions

来源：评论

学校读者我要写书评

暂无评论

Contour smoothing algorithm based on contour extremes

Contour smoothing algorithm based on contour extremes

引用

2016 International Conference on Interfaces and Human Computer Interaction, IHCI 2016, Game and Entertainment Technologies, GET 2016 and Computer Graphics, visualization, Computer vision and image processing, CGvCvIP 2016

作者： Koriukalov, Oleksandr v. Tereshchenko, vasyl M. Taras Shevchenko National University of Kyiv Glushkova st. 4d Kyiv83000 Ukraine

ISBN: (纸本)9789898533524

In this article we propose linear time algorithm for contour smoothing, based on finding extremes. First we find vertexes where contour convexity changes, than obtain local minimums, maximums and points of support, which should be used in resulting contour. The main goal of proposed approach is to compute accurate interior area of a bounding contour, it was successfully applied for recovering object contour after segmentation algorithms or human annotations, for contours noise reduction after jpeg compression.

关键词： Noise abatement

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：