检索结果-南通市图书馆

稀有金属材料与工程 2012年第S1期41卷 296-298页

作者： Zhu Lina1,2,Xu Binshi2,Wang Haidou2,Wang Chengbiao1 1 School of Engineering and Technology,china University of Geosciences,Beijing 100083,china 2 national Key laboratory for Remanufacturing,Academy of Armored Forces Engineering,Beijing 100072,china Acad Armored Forces Engn Natl Key Lab Remfg Beijing 100072 Peoples R China china Univ Geosci Sch Engn & Technol Beijing 100083 Peoples R China

In this paper,NiCr-Cr3C2 coating was deposited onto AISI 1045 steel substrate by employing supersonic plasma spraying *** surface and cross-section morphologies of the NiCr-Cr3C2 coating were observed by *** phase constituents of the coating were identified by *** SEM images showed that the coating was very dense,and it had a low porosity *** XRD pattern implied that the coating was mainly composed of NiCr,Cr3C2 and *** tests were performed on the coating surface by a Nano *** widely used Oliver-Pharr method was adopted to extract the mechanical properties of the *** hardness exhibited a strong peak-load-dependence,*** size effect;the elastic modulus was not affected by indentation size effect.

关键词： nanoindentation mechanical property indentation size effect

Gravel Image Segmentation in Noisy Background Based on Partial Entropy Method

在线全文

学校读者我要写书评

暂无评论

Journal of Earth Science 2000年第1期19卷 94-96页

作者： Wang Guangjun Tian Jinwen Chen Zhenyu Liu JianState Key laboratory for Image Processing and Intelligent Control, Institute for pattern recognition and Artificial Intelligence, Huazhong University of Science and Technology, WuHan 430074 Wu Guoping

Because of wide variation in gray levels and particle dimensions and the presence of many small gravel objects in the background, as well as corrupting the image by noise, it is difficult to segment gravel objects. In this paper, we develop a partial entropy method and succeed to realize gravel objects segmentation. We give entropy principles and fast calculation methods. Moreover, we use minimum entropy error automaticly to select a threshold to segment image. We introduce the filter method using mathematical morphology. The segment experiments are performed by using different window dimensions for a group of gravel image and demonstrates that this method has high segmentation rate and low noise sensitivity.

关键词： partial entropy segmentation mathematical morphology gravel threshold filter.

NONMONOTONIC　TRUTH　MAINTENANCE　SYSTEMS

在线全文

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 1996年第1期1卷 83-87页

作者： Yang Jie Shi Pengfei (Institute of Image Processing and pattern recognition)

ＮＯＮＭＯＮＯＴＯＮＩＣＴＲＵＴＨＭＡＩＮＴＥＮＡＮＣＥＳＹＳＴＥＭＳ＊ＹａｎｇＪｉｅＳｈｉＰｅｎｇｆｅｉ（ＩｎｓｔｉｔｕｔｅｏｆＩｍａｇｅＰｒｏｃｅｓｓｉｎｇａｎｄＰａｔｅｒｎＲｅｃｏｇｎｉｔｉｏｎ）Ａｂｓｔｒａｃ... 详细信息

ＮＯＮＭＯＮＯＴＯＮＩＣＴＲＵＴＨＭＡＩＮＴＥＮＡＮＣＥＳＹＳＴＥＭＳ＊ＹａｎｇＪｉｅＳｈｉＰｅｎｇｆｅｉ（ＩｎｓｔｉｔｕｔｅｏｆＩｍａｇｅＰｒｏｃｅｓｓｉｎｇａｎｄＰａｔｅｒｎＲｅｃｏｇｎｉｔｉｏｎ）ＡｂｓｔｒａｃｔＴｒｕｔｈｍａｉｎｔｅｎａｎｃｅ...

关键词： artificial intelligence nonmonotonic truth maintenance stratified truth maintenance nonmonotonic reasoning

Salient region detection and segmentation for general object recognition and image understanding

在线全文

学校读者我要写书评

暂无评论

Science china(Information Sciences) 2011年第12期54卷 2481-2490页

作者： HUANG TieJun 1 , TIAN YongHong 1 , LI Jia 2 & YU HaoNan 11 national Engineering laboratory for Video Technology, School of Electrical Engineering and Computer Science, Peking University, Beijing 100871, china 2 Key laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, china national Engineering laboratory for Video Technology School of Electrical Engineering and Computer Science Peking University Beijing China Key laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

General object recognition and image understanding is recognized as a dramatic goal for computer vision and multimedia retrieval. In spite of the great efforts devoted in the last two decades, it still remains an open problem. In this paper, we propose a selective attention-driven model for general image understanding, named GORIUM (general object recognition and image understanding model). The key idea of our model is to discover recurring visual objects by selective attention modeling and pairwise local invariant features matching on a large image set in an unsupervised manner. Towards this end, it can be formulated as a four-layer bottom-up model, i.e., salient region detection, object segmentation, automatic object discovering and visual dictionary construction. By exploiting multi-task learning methods to model visual saliency simultaneously with the bottom-up and top-down factors, the lowest layer can effectively detect salient objects in an image. The second layer exploits a simple yet effective learning approach to generate two complementary maps from several raw saliency maps, which then can be utilized to segment the salient objects precisely from a complex scene. For the third layer, we have also implemented an unsupervised approach to automatically discover general objects from large image set by pairwise matching with local invariant features. Afterwards, visual dictionary construction can be implemented by using many state-of-the-art algorithms and tools available nowadays.

关键词： object recognition image understanding visual saliency salient object segmentation visual dictionary

Terrain Simplification Research in Augmented Scene Modeling

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of china University of Geosciences 2001年第4期12卷 351-355页

作者： Ming Delie You Kefei Tian Jinwen Liu Jian State Key laboratory for Image Processing and Intelligent Control, Institute for pattern recognition and Artificial Intelligence , Huazhong University of Science and Technology , Wuhan 430074 Wang Guangju State Key laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 Faculty of Information Engineering China University of Geosciences Wuhan 430074

Augmented reality is the merging of synthetic sensory information into a user's perception of a real environment. As one of the most important tasks in augmented scene modeling, terrain simplification research has gained more and more attention. In this paper, we mainly focus on point selection problem in terrain simplification using triangulated irregular network. Based on the analysis and comparison of traditional importance measures for each input point, we put forward a new importance measure based on local entropy. The results demonstrate that the local entropy criterion has a better performance than any traditional methods. In addition, it can effectively conquer the 'short-sight' problem associated with the traditional methods.

关键词： augmented reality scene modeling terrain simplification triangulated irregular network importance measures local entropy.

An Improved Explicit Integration for Nonrigid Simulation

在线全文

学校读者我要写书评

暂无评论

International Journal of Systems and Control

International Journal of Systems and Control 2008年第1期 48-56页

作者： HU Xinrong, LI Dehua Institute for pattern recognition and Artificial Intelligence, State Education Commission laboratory for Image Processing and Intelligence Control,HuaZhong Univ. of Science&Technology, Wuhan 430074,china

Nonrigid simulation is a hard but challengeable work to all graphics researchers. A satisfied nonrigid simulation should be general, accurate, efficient and stable. Explicit, implicit and semi-implicit integration methods have contributed to large performance enhancements in the field of nonrigid simulation. Cloth is the most representative nonrigid object. In this paper, we propose an improved explicit integration--embedded Runge-Kutta method to solve the nonrigid simulation that takes cloth for example based on classical spring-mass model. Traditional embedded Runge-Kutta methods generally apply some optimized coefficients to solve ordinary differential equations of nonrigid simulation. Most of them tend to concentrate on the efficiency of the simulation process, and not the fidelity of the simulation result. We investigate and determine the extent to which the overall quality must be compromised in order for the stable conditions to be satisfied. The improved integration method proposed in our paper incorporates the fixed timestep and adaptive timestep in solving cloth motion equations to achieve a controllable error evaluation. Compared with the other Runge-Kutta methods, the proposed method has some advantages for nonrigid simulation: controllable error evaluation without extra computations, excellent efficiency, good stability and satisfied precision. Experiment demonstrates that this method results in simulation efficiency improvements and is considerable practicable.

关键词： Nonrigid simulation Explicit integration Ordinary differential equation Spring-mass model Timestep

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

基于联想记忆的触觉图象识别

机器人 1993年第6期15卷 48-51页

作者：胡维真顾学真中国科学院自动化研究所模式识别国家重点实验室北京100080

与视觉相比,机器人触觉图象具有分辨率低、噪声大、信息不完整等特点,若采用常规分类器,识别率往往不高.本文基于 Hopfield 联想记忆神经网络,构造了一种适合于识别信息不完整、噪声较大的图象的分类器,并成功地应用于智能机器人触觉图... 详细信息

与视觉相比,机器人触觉图象具有分辨率低、噪声大、信息不完整等特点,若采用常规分类器,识别率往往不高.本文基于 Hopfield 联想记忆神经网络,构造了一种适合于识别信息不完整、噪声较大的图象的分类器,并成功地应用于智能机器人触觉图象的识别.通过实验,我们对这种分类器的性能与三种常规分类器——最小距离、最近邻和贝叶斯分类器作了比较.

关键词：人工神经网络 Hopfield 模型联想记忆机器人触觉图象识别

在线全文

学校读者我要写书评

暂无评论

基于动态基元选取的真实感可视语音合成系统

系统仿真学报 2008年第S1期20卷 420-422,426页

作者：周密穆凯辉陶建华中科院自动化所模式识别国家重点实验室北京100190

伴有说话者面部表情及唇动的文本-可视语音转换系统(TTVS)能够大大增强人机交互的生动性和真实感。结合当前主要的两类TTVS技术,利用数据驱动法中的动态基元拼接获得参数序列,驱动MPEG-4人脸动画模型,在保留灵活性和可移植性等优点的前... 详细信息

伴有说话者面部表情及唇动的文本-可视语音转换系统(TTVS)能够大大增强人机交互的生动性和真实感。结合当前主要的两类TTVS技术,利用数据驱动法中的动态基元拼接获得参数序列,驱动MPEG-4人脸动画模型,在保留灵活性和可移植性等优点的前提下,以较小的数据量,获得了较为生动的效果,形成了具有较高真实感的中文可视语音合成系统。

关键词：可视语音动态基元拼接可视韵律 MPEG-4

Prediction of Enthalpies of Fusion for Divalent Rare Earth Halides Based on Modeling by Artificial Neural Networks and pattern recognition

在线全文

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 1999年第1期13卷 24-26页

作者： Yimin Sun Zhiyu Qiao Minghong He(Applied Science School, University of Science & Technology Beijing, Beijing 100083, china)(national Natural Science Foundation of china, Beijing 100083, china) Applied Science School University of Science and Technology Beijing Beijing 100083 China national Natural Science Foundation of china Beijing 100083 China

The artificial neural network (ANN) and the pattern recognition were applied to study the correlation of enthalpies of fusion for divalent rare earth halides with their microstructural parameters,such as ionic radius and electronegativity. The model,represented by a back-propagation netal network, was trained with a 12 set of published data for divalent rare earth halides and then was used to predict the unknown ones. Also the criterion equations were ptesented to determine the enthalpies of fuSion for divalent rare earth halides using pattern recognition in mis work. The results from the model in ANN and criterion equations are in very good agreement with reference data.

关键词： BP neural network pattern recognition enthalpy of fusion divalent rare earth halides microstructural parameters