检索结果-内蒙古大学图书馆

IEEE International Symposium on Biomedical Imaging

作者： N. El-Zehiry M. Casanova H. Hassan A. Farag Computer Vision and Image Processing Laboratory University of Louisville USA Department of Psychiatry and Behavioral Sciences University of Louisville USA

The minicolumn is generally considered the basic unit of the neocortex in all the mammalian brains. Enlargement of the cortical surface is believed to occur through the addition of minicolumns rather than a single neuron. This study aims at testing the hypothesis that brain developmental disorders can be diagnosed and analyzed in terms of the minicolumnar disturbance. To do this, we propose to correlate the pathological findings in terms of the minicolumnar structure to the MRI findings in terms of volumetric analysis

关键词： Magnetic resonance imaging Neurons Autism Pathology Aging Computer vision image processing Psychiatry Testing Nerve fibers

来源：评论

学校读者我要写书评

暂无评论

An Information Theoretic Criterion for image Quality Assessment Based on Natural Scene Statistics

An Information Theoretic Criterion for Image Quality Assessm...

引用

IEEE International Conference on image processing

作者： Di Zhang Ed Jernigan Laboratory of Vison and Image Processing Department of Systems Design Engineering University of Waterloo ONT Canada

Measurement of visual quality is crucial for various image and video processing applications. Traditional measurements convert the spatial data into some feature domain, such as the Fourier domain, and detect the similarity, such as mean square distance or Minkowsky distance, between the test data and the reference or perfect data. In this paper we approach image quality assessment by presenting a novel information theoretic criterion based on natural scene statistics. Using Gaussian scale mixture model in an information theoretic framework, we design an algorithm to compute the minimum perceptual information contained in the images and evaluate the image quality in the form of entropy. Finally, our algorithm is validated with a database set containing 982 images.

关键词： image quality Layout Statistics Humans Nonlinear distortion Testing Entropy GSM Visual system Distortion measurement

来源：评论

学校读者我要写书评

暂无评论

Quantization-based probabilistic feature modeling for kernel design in content-based image retrieval

Quantization-based probabilistic feature modeling for kernel...

引用

8th ACM Multimedia International Workshop on Multimedia Information Retrieval, MIR 2006, co-located with the 2006 ACM International Multimedia Conferenc

作者： Xie, Hua Andreu, Victor Ortega, Antonio Jet Propulsion Laboratory California Institute of Technology 4800 Oak Grove Drive Pasadena CA 91109 Signal and Image Processing Institute Department of Electrical Engineering-Systems University of Southern California Los Angeles CA 90089

ISBN: (纸本)1595934952

In this paper, a quantization-based probabilistic feature modeling approach is proposed for relevance feedback in content-based image retrieval. We demonstrate its performance by using the resulting models within a support vector machine (SVM) based technique. Each feature component is quantized and mapped to probabilistic quantities representing the likelihood of the image being relevant (and irrelevant). These probabilistic quantities are then used to derive an information divergence-based kernel function for SVM classification which we introduced in earlier work. We show that the proposed method leads to the optimal maximum likelihood solution as the knowledge of the actual underlying probability model improves (i.e.,as the feature space is partitioned into arbitrarily small "regions "and accurate models are known for all regions). vWe investigate several practical quantization designs for feature modeling specifically in relevance feedback applications,where the scarcity of the data and high dimensionality prevent usage of vector quantization and parametric modeling *** proposed framework naturally takes into account the statistics of the data that is available during relevance feedback for the purpose of discriminating between relevant and irrelevant *** with the Corel dataset show that quantizers specifically designed for this application achieve gains over simple uniform quantizers (e.g.,5% to 10% in retrieval accuracy) when combined with our information divergence kernel. This kernel achieves gains (e.g.,17% in retrieval accuracy after first relevance feedback)as compared to the standard radial basis function (RBF) kernel used for SVM-based relevance feedback. Copyright 2006 ACM.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Multiresolution Object Recognition Using Dual Heuristic Programming

Multiresolution Object Recognition Using Dual Heuristic Prog...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： F. Siddiqui K.M. Iftekharuddin Intelligent Systems and Image Processing Laboratory Department of Electrical and Computer Engineering University of Memphis Memphis TN USA

We present automatic target recognition (ATR) model based on principles of biological vision systems. The model employs reinforcement learning (RL) through Dual Heuristic Programming (DHP). The performance of the reported ATR model is compared to that of our previously reported ATR model, based on Heuristic Dynamic Programming (HDP). The HDP and DHP, known as the Adaptive Critic Designs (ACD), are neural network based implementation of Dynamic Programming (DP). The simulation shows promising results for both HDP and DHP based ATR model in presence of resolution distortion in incoming images and confirms that the DHP model is faster and more robust for our ATR system than the HDP.

关键词： Object recognition Learning Robustness Biological system modeling Machine vision Target recognition Dynamic programming Neural networks image resolution Nonlinear distortion

来源：评论

学校读者我要写书评

暂无评论

Multiresolution Approach for Non-Contact Measurements of Arterial Pulse using Thermal Imaging

Multiresolution Approach for Non-Contact Measurements of Art...

引用

IEEE Computer Society Conference on Computer vision and Pattern Recognition Workshops (CVPRW)

作者： S.Y. Chekmenev A.A. Farag E.A. Essock Computer Vision and Image Processing Laboratory University of Louisville Louisville KY USA Department of Psychological and Brain University of Louisville Louisville KY USA

This paper presents a novel, multiresolution (MR) approach for non-contact passive measurements of the arterial pulse along the arterial tree using thermal imaging of the most accessible regions of human face and neck. The method automatically detects Region/s Of Measurement (ROM) of the arterial pulse using the periodic nature of arterial thermal patterns. This ROM constitutes a skin area where the heat pulsation produced by an artery is most pronounced. The output of the algorithm is a descriptive arterial pulse waveform. To the best of our knowledge, our results are novel and have not been reported before. Some potential applications of this work are in the field of non-contact health state/ physiology monitoring, magnetic resonance imaging, smart rooms, polygraph testing, and intent identification.

关键词： Pulse measurements image resolution Read only memory Humans Face detection Neck Skin Arteries Physiology Monitoring

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Human Verification Using Face and Speech

Multi-Modal Human Verification Using Face and Speech

引用

IEEE International Conference on Computer vision systems (ICVS)

作者： Changhan Park Joonki Paik Taewoong Choi Soonhyob Kim Youngouk Kim J. Namkung Image Processing and Intelligent Systems Laboratory Department of Image Engineering Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul South Korea Multimedia Signal Processing Laboratory Kwangwoon University Seoul South Korea Precision Machinery Center Korea Electronics and Technology Institute Puchon Gyeonggi South Korea Intelligent Image Communication Laboratory Department of Computer Engineering Kwangwoon University Seoul South Korea

In this paper, we propose a personal verification method using both face and speech to improve the rate of single biometric verification. False acceptance rate (FAR) and false rejection rate (FRR) have been a fundamental bottleneck of real-time personal verification. The proposed multimodal biometric method is to improve both verification rate and reliability in real-time by overcoming technical limitations of single biometric verification methods. The proposed method uses principal component analysis (PCA) for face recognition and hidden markov model (HMM) for speech recognition. It also uses fuzzy logic for the final decision of personal verification. Based on experimental results, the proposed system can reduce FAR down to 0.0001%, which provides that the proposed method overcomes the limitation of single biometric system and provides stable personal verification in real-time.

关键词： Humans Speech Face detection Face recognition Biometrics Principal component analysis Feature extraction Hidden Markov models image edge detection Laboratories

来源：评论

学校读者我要写书评

暂无评论

The "4K Pure Cinema" joint digital cinema trial

引用

NTT Technical Review 2006年第7期4卷 18-21页

作者： Sakamoto, Hideki Minami, Kenichi Shirakawa, Kazuhiro Fujii, Tetsuro Saito, Yukihisa Yamane, Hiroshi NTT Department III Chiyoda-ku Tokyo 100-8116 Japan Media Processing Systems Research Group NTT Network Innovation Laboratories IEEE Information Processing Society of Japan of Japan Media Networking Laboratory NTT Network Innovation Laboratories IEICE Broadband Application Service Department NTT West Institute of Image Information and Television Engineers of Japan Institute of Image Electronics Engineers of Japan

We describe a trial of the distribution of the latest Hollywood movies in digital data format to theaters in Japan via a network for projection as digital cinema (4K Pure Cinema). It is a joint effort by NTT and NTT West, in cooperation with Warner Bros. Entertainment, Warner Entertainment Japan, and Toho. It began in October 2005 and is still in progress.

关键词： Digital television

来源：评论

学校读者我要写书评

暂无评论

CNNUM-Based Methods Using Deformable Contours on Smooth Boundaries

CNNUM-Based Methods Using Deformable Contours on Smooth Boun...

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： Tamas Szabo Peter Szolgay Department of Image Processing and Neurocomputing Faculty of Information Technology University of Pannonia Veszprem Hungary Analogical and Neural Computing Systems Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

In this paper two methods are presented. A CNNUM-based method is shown to quantify the displacement of the normal interhemisperic bilateral symmetry line. The method uses a deformable open contouring technique. Anothe... 详细信息

关键词： Active contours Computed tomography Magnetic resonance Anatomical structure image segmentation Biomedical imaging Electronic mail Computer networks Pixel image resolution

来源：评论

学校读者我要写书评

暂无评论

Tillarom: An AJAX based folk song search and retrieval system with gesture interface based on kodály hand

Tillarom: An AJAX based folk song search and retrieval syste...

引用

1st ACM International Workshop on Human-Centered Multimedia, HCM 2006, co-located with the 2006 ACM International Multimedia Conference

作者： Licsár, Attila Szirányi, Tamás Kovács, László Pataki, Balázs University of Pannonia Department of Image Processing and Neurocomputing Egyetem u. 10 H-8200 Veszprém Hungary Department of Distributed Systems Computer and Automation Research Institute Hungarian Academy of Sciences Lágymányosi u. 11 H-1111 Budapest Hungary Analogical and Neural Computing Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences Lágymányosi u. 11 H-1111 Budapest Hungary

ISBN: (纸本)1595935002

A digital folk song search and retrieval system with a hand gesture based interface is presented. Tillarom is a comprehensive collection of original Hungarian folk songs recorded using different technologies such as phonographs and/or stereo DAT cassettes. This digital archive contains professional quality metadata records as well as MIDI recordings for presenting the different types of clustered folk songs. An AJAX based search and retrieval interface was developed that can be used together with optically recognized Kodály's hand signs to formulate queries through a web browser. The appearance based recognition of hand gestures utilizes contour analysis and SVM based classification. We evaluated the performance of the recognition of hand signs and investigated the main problems of their usage in our system. Copyright 2006 ACM.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

Minimal Circuit and State Space Realization of Generalized 3-D Lattice-Ladder Discrete Filters

Minimal Circuit and State Space Realization of Generalized 3...

引用

Proceedings of 2006 IEEE International Symposium on Circuits and systems,Volume 4

作者： George E. Antoniou Image Processing and Systems Laboratory Department of Computer Science Montclair State University Montclair NJ USA

In this paper a circuit realization is presented for generalized three-dimensional (3-D) lattice discrete systems/filters. The proposed structure has minimum number of delay elements. Based on this circuit realization the corresponding state space realization-representation is derived. The dimension of the 3-D state space vector is minimal and the corresponding transfer function is characterized by the well known all-pass filter property.

关键词： Circuits State-space methods Lattices Transfer functions image processing Digital filters Signal processing Polynomials Adaptive filters Nonlinear filters

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：