检索结果-内蒙古大学图书馆

On the simulation of expressional animation based on facial MoCap

Science China(Information Sciences) 2013年第10期56卷 265-276页

作者： FANG XiaoYong WEI XiaoPeng ZHANG Qiang ZHOU ChangJun Key Laboratory of Advanced Design and Intelligent Computing (Dalian University) Ministry of Education School of Management Dalian University of Technology

MoCap(motion capture)-based animation is a hot issue in computer animation research *** on the optical MoCap system,this paper proposes a novel cross-mapping based facial expression simulating *** overcome the problem of the false upper and lower jaw correlation derived from the facial global RBFbased cross-mapping method,we construct a functional partition based RBF cross-mapping *** model animating,enhanced markers are added and animated by our proposed skin motion *** addition,based on the enhanced markers,an improved RBF-based animating approach is raised to derive realistic facial *** more,a pre-computing algorithm is presented to reduce computational cost for real-time *** experiments proved that the method can not only map the MoCap data of one subject to diferent personalized faces but generate realistic facial animation.

关键词： facial animation cross-mapping functional partition motion mechanism RBF

来源：评论

学校读者我要写书评

暂无评论

Scattered data processing approach based on optical facial motion capture

引用

Applied Bionics and Biomechanics 2013年第2-3期10卷 75-87页

作者： Zhang, Qiang Liang, Xiaoying Wei, Xiaopeng Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian 116622 China

In recent years, animation reconstruction of facial expressions has become a popular research field in computer science and motion capture-based facial expression reconstruction is now emerging in this field. Based on the facial motion data obtained using a passive optical motion capture system, we propose a scattered data processing approach, which aims to solve the common problems of missing data and noise. To recover missing data, given the nonlinear relationships among neighbors with the current missing marker, we propose an improved version of a previous method, where we use the motion of three muscles rather than one to recover the missing data. To reduce the noise, we initially apply preprocessing to eliminate impulsive noise, before our proposed three-order quasi-uniform B-spline-based fitting method is used to reduce the remaining noise. Our experiments showed that the principles that underlie this method are simple and straightforward, and it delivered acceptable precision during reconstruction. © 2013 - IOS Press and the authors. All rights reserved.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Research on Image Based on Improved SURF Feature Matching

Research on Image Based on Improved SURF Feature Matching

引用

International Symposium on Computational Intelligence and design, ISCID

作者： Yanling Liu Sihang Ma Tianjin Key Laboratory of the Design and Intelligent Control of the Advanced Mechatronical System Tianjin University of Technology China

ISBN: (纸本)9781479970063

Image matching is widely used in machine vision, computer technology, industry and agriculture and other fields. Matching the characteristics of traditional methods such as SIFT has advantages of compressed information quantity, high precision, but there are also some deficiencies such as the large of calculation, long time, the object to be measured of position should be required accurately and etc. This paper presents image matching method based on improved SURF feature, and the analysis and comparison are made for the three kinds of image matching methods. The experiment proved: Sometimes it can also be A single SIFT or SURF, The improved SURF more can meet the requirements of parameter estimation accuracy and real-time. It can carry out accurate judgment, recognition for the digital image. It has certain theoretical value and practical value.

关键词： Feature extraction Image matching Vectors Accuracy Algorithm design and analysis Histograms Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Chinese microblogging emotion classification based on support vector machine

Chinese microblogging emotion classification based on suppor...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Xiao Sun Chengcheng Li Jiaqi Ye Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China

ISBN: (纸本)9781479926978

Through the analysis and study of the emotional characteristics in Chinese micro-blog, this paper proposed a multidimensional sentiment classification method based micro-blog emotion classification, emoticon in micro-blog is adopted to train the support vector machine and divide micro-blog into seven types of emotions: happiness, fondness, sorrow, anger, fear, detestation and surprise. We used micro-blog emoticon to initial screen large-scale unmarked data, and automatically labeled them into seven types, then used this emotional corpus as training set to train the emotion classifier to classify micro-blog data into multiple emotion categories. The experimental results show that precision of unigram model for each type can reach 63.7%. Meanwhile, different feature selection methods for support vector machines and Naive Bayes classifier experiment have been adopted in the experiment, the precision and recall has reached more than 71%.

关键词： Accuracy Support vector machines Twitter Niobium Training Blogs Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Hybrid model based sentiment classification of Chinese micro-blog

Hybrid model based sentiment classification of Chinese micro...

引用

International Conference on Audio, Language and Image Processing, ICALIP

作者： Xiao Sun Chengcheng Li Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China

ISBN: (纸本)9781479939046

Through analysis and study of emotional characteristics in Chinese micro-blog, such as Sina Weibo, this paper proposed a multidimensional sentiment classification method based on micro-blog emoticon by dividing micro-blog into 7 types of emotions categories: happiness, fondness, sorrow, anger, fear, detestation and surprise. We used predefined micro-blog emoticon sets to initial screen large-scale unmarked data, and automatically labeled them, then used this emotional corpus as training set to train the emotion classifier, which divided micro-blog data into multiple emotion categories. The experimental results show that accuracy rate of using unigram model for each class can reach 63.7%. And the adoption of different feature selection methods for Support Vector Machines and Naive Bias classifier experiment, by which the obtained accuracy rate and recall rate has reached higher than 71%.

关键词： Accuracy Blogs Support vector machines Twitter Niobium Educational institutions Training

来源：评论

学校读者我要写书评

暂无评论

FRUIT RECOGNITION BASED ON MULTI-FEATURE AND MULTI-DECISION

FRUIT RECOGNITION BASED ON MULTI-FEATURE AND MULTI-DECISION

引用

2014 IEEE 3rd International Conference on Cloud computing and Intelligence Systems

作者： Xiaohua Wang Wei Huang Chao Jin Min Hu Fuji Ren Affective Computing and Advanced Intelligent Machines Anhui Key Laboratory School of Computer and Information Hefei University of Technology

In order to overcome the existing fruit recognition method only for single feature recognition which leads the problem of lower recognition rate,this paper proposes a recognition method based on multi-feature and ***,we preprocess the fruit image which is to be classified,separateing foreground and background,and then we divide the target ***,in order to take full advantage of multi-independence and complementarity between features,we extract the color,shape and texture of fruits image and put these features into the BP neural network to ***,the results of different features are put into the decision-making mechanisms to obtain a final recognition *** experiment results on object library and self-built library that is built by ourselves show that the method has good identification ability to fruit recognition and achieve the goal to identify different fruit.

关键词： fruit features BP neural network multi-feature multi-decision

来源：评论

学校读者我要写书评

暂无评论

design and realization of 3D NOC multicast router base on multicast rotational routing arithmetic

Design and realization of 3D NOC multicast router base on mu...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Wei Wang Runfeng Li Fang Fang Tian Chen Fuji Ren Jun Liu Xi Wu Hefei University of Technology Hefei China Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine China

ISBN: (纸本)9781479926978

Traditional 3D NoC router may encounter the situations of congestion and hot spot. And it also doesn't have the function of multicast. In this paper, we present a new routing arithmetic called Multicast Rotational Routing Arithmetic (MRRA). It can handle several destination addresses at the same time, recombine packets, sent the same data to the different destination nodes, and avoid the congestion. The proposed algorithm is implemented by the new multicast 3D NoC router which is also proposed in this paper. The 3D NoC router is designed in Verilog HDL, simulated by Modelsim, synthesized and prototyped by Synplify and FPGA respectively. The experiment results show that the multicast router of MRRA can achieve a very good performance in terms of throughput and delay. The increased area utilization also can be tolerated.

关键词： Routing Three-dimensional displays Throughput Algorithm design and analysis Ports (Computers) Hardware design languages Integrated circuits

来源：评论

学校读者我要写书评

暂无评论

A test data compression scheme based on position information coding

A test data compression scheme based on position information...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Tian Chen Bingdong Yang Wei Wang Birong Hao Fuji Ren Jun Liu YiXin Wang AnHui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei The University of Tokushima Japan

ISBN: (纸本)9781479926978

Under the condition of Built-off Self-test (BOST), a novel test data compression scheme based on position information coding is presented, which is targeting test data and test power consumption. The proposed scheme gets the next test stimuli by reversing some bits of the responses corresponding to the previous test vectors. During the process of bit flip, test power problem should be taken into account; both the shift power and capture power during the test should be limited in the scope of security. For shift power, need to modify the scan chain by adding blocking logic; and the capture power reduction through the test cube filling based on the response. Experimental results justify the efficacy of the proposed method in attaining test-data compression; the average compression ratio is 73.63% on the premise of capture power consumption reduced by 20%.

关键词： Encoding Hamming distance Test data compression Radiation detectors Hardware Sorting Built-in self-test

来源：评论

学校读者我要写书评

暂无评论

WEWATCH:BI-SCREEN VIDEO WATCHING EXPERIENCE ON SMART DEVICES

WEWATCH:BI-SCREEN VIDEO WATCHING EXPERIENCE ON SMART DEVICES

引用

2014 IEEE 3rd International Conference on Cloud computing and Intelligence Systems

作者： Fuji Ren Mengni Chen Yu Gu Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computing and InformationHefei University of Technology Dept.of Information Science & Intelligent Systems Univ.of TokushimaJapan

The high resolution and widescreen mobile devices have tremendous applications in our daily *** this paper,we demonstrate a specific bi-screen video sharing application called WeWatch that a high resolution video is played across screens of two mobile *** helps users to enhance their watching experience on the Android *** order to efficiently use idle mobile devices,we develop a novel algorithm to share videos with devices with different screen sizes and *** research provides a method which automatically controls videos based on different distances between *** distance is determined by the empirical WiFi RSSI values obtained through the experimental *** have prototyped the system and conducted a real-world energy efficiency and user experience *** show that WeWatch has negligible impact on battery lifetime while over 80%users like our application.

关键词： Video Sharing Screen adaptation Distance detection Energy efficiency.

来源：评论

学校读者我要写书评

暂无评论

A Connected Component-Based Distributed method for overlapping community detection 5

A Connected Component-Based Distributed method for overlappi...

引用

5th International Conference on computing Communication and Networking Technologies, ICCCNT 2014

作者： Chen, Tian Liu, Kai Yi, Xin Shen, Dandan Wang, Wei Ren, Fuji Liu, Jun School of Computer and Information Hefei University of Technology Hefei230009 China Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei230009 China AnHui Agricultural University Hefei230036 China University of Tokushima 770-8506 Japan

ISBN: (纸本)9781479926961

In order to find the overlapping community structure more quickly and accurately in complex network, this paper proposes a Connected Component-Based Distributed method (CCBD) for overlapping community detection. CCBD first divides edges set in the network into smaller one. Next, it seeks out connected component using distributed platforms and gives a serials number to them according to certain rules. Then, it classifies these connected components according to the serials number. Task nodes determine whether any two connected components and non-propagating edges can be connected to become a larger community. Finally, CCBD negotiates a new serials name for the new community. Through repeated iterations, we get the community structure in the network. Nodes belong to multiple communities are overlapping nodes. Experiment results show that CCBD has higher time efficiency benefiting from distributed computing. Moreover, the quality of communities detected by CCBD surpasses those found by other algorithms. © 2014 IEEE.

关键词： Complex networks

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：