检索结果-内蒙古大学图书馆

International Conference on pattern recognition

作者： M. Lettner R. Sablatnig Pattern Recognition and Image Processing Group Institute of Computer Aided Automation University of Technology Vienna Vienna Austria

ISBN: (纸本)0769525210

In this study we analyze texture and profile features of painted strokes in order to identify the drawing media used for sketching underdrawings. Underdrawings are preliminary drawings on the panel prepared for paintings and are unseen in the finished work. Cameras working in the near infrared range allow the visualization of underdrawings. Due to the tiny width of the strokes we perform an alignment of the feature extraction windows in order to obtain a major content of the stroke texture. The method is tested on strokes applied on test panels and underdrawing strokes in IR images of medieval paintings

关键词： Painting Testing pattern recognition image texture analysis Feature extraction image analysis Paints Art Technological innovation Silver

来源：评论

学校读者我要写书评

暂无评论

Bidirectional feature selection method based on mutual information and redundancy-synergy coefficient

引用

Journal of Harbin institute of Technology (New Series) 2006年第3期13卷 299-306页

作者： Yang, Sheng Zhang, Zhi Shi, Peng-Fei School of Computer and Communication Hunan University Changsha 410082 China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai 200030 China

Feature subset selection is a fundamental problem of data mining. The mutual information of feature subset is a measure for feature subset containing class feature information. A hashing mechanism is proposed to calculate the mutual information of feature subset. The feature relevancy is defined by mutual information. Redundancy-synergy coefficient, a novel redundancy and synergy measure for features to describe the class feature, is defined. In terms of information maximization rule, a bidirectional heuristic feature subset selection method based on mutual information and redundancy-synergy coefficient is presented. This study's experiments show the good performance of the new method.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Recent Progress in Computerization of TCM

引用

通讯和计算机（中英文版） 2006年第7期3卷 78-81页

作者： Zhi Liu Jingqi Yan Qunlin Tang Qingli Li Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200240 China Shenzhen Graduate School of Harbin Institute of Technology Shenzhen 518055 China

The principles of Traditional Chinese Medical (TCM) diagnosis are based on the information obtained from four diagnostic processes, which are inspection, listening and smelling, inquiry and palpation. These diagnosis methods mainly rely on the experiences of the doctors. With the development of information technology, computerization of the diagnosis method is urgent. However, there are so many challenges in this field. This paper will provide detailed introduction of these contents. Through it, the state of arts of the computerization of TCM and the existing challenge of this field can be gotten.

关键词：终端设备至计算机多路转接器生物工程计算机化计算机技术

来源：评论

学校读者我要写书评

暂无评论

Robot Position Identification by Actively Localizing Sound Beacons

Robot Position Identification by Actively Localizing Sound B...

引用

IEEE Instrumentation and Measurement Technology Conference

作者： Jie Huang Satoshi Ishikawa Michiko Ebana Huakang Li Qunfei Zhao School of computer science and engineering University of Aizu Japan Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University China

In this paper, we proposed a robot self position identification method by active sound localization. This method can be used for autonomous security robots working in room environments. A system using a AIBO robot equipped with two microphones and wireless network is constructed and is used for position identification experiments. Arrival time differences to the microphones of robot are used as localization cues. To overcome the ambiguity of front-back confusion, a three-head position measurement method was proposed. The robot position can be identified by the intersection of circles restricted by the azimuth differences to different speaker pairs. By localizing three or four speakers as sound beacons positioned on known locations, the robot can identify its self position with an average error of about 7 cm in a 2.5 times 3.0 m 2 working space

关键词： Microphones Loudspeakers Humans Head Azimuth Orbital robotics Mobile robots Humanoid robots image processing Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

3D and Infrared Face Reconstruction from RGB data using Canonical Correlation Analysis

3D and Infrared Face Reconstruction from RGB data using Cano...

引用

International Conference on pattern recognition

作者： M. Reiter R. Donner G. Langs H. Bischof Pattern Recognition and Image Processing Group Vienna University of Technology Austria Graz University of Technology Institute for Computer Graphics and Vision Austria

In this paper, we apply a multiple regression method based on canonical correlation analysis (CCA) to face data modelling. CCA is a factor analysis method which exploits the correlation between two high dimensional signals. We first use CCA to perform 3D face reconstruction and in a separate application we predict near-infrared (NIR) face texture. In both cases, the input data are color (RGB) face images. Experiments show, that due to the correlation between input and output signal, only a small number of canonical factors are needed to describe the functional relation of RGB images to the respective output (NIR images and 3D depth maps) with reasonable accuracy

关键词： Shape Face detection Lighting image reconstruction image analysis image databases pattern analysis Rendering (computer graphics) image color analysis pattern recognition

来源：评论

学校读者我要写书评

暂无评论

TONGUE SHAPE DETECTION BASED ON B-SPLINE

TONGUE SHAPE DETECTION BASED ON B-SPLINE

引用

2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)

作者： LIU ZHI JING-QI YAN TAO ZHOU QUN-LIN TANG Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 2000 the graduate school of Harbin Institute of Technology Shenzhen 5180055 China

Human tongue is the only organ of human, which can be laid out. It takes an important role in Traditional Chinese Medicine (TCM) because of its abundant biomedical information. With the progress of modernization of TCM,computerization of tongue diagnosis attracts the researchers'interesting. Thus, how to get an accurate tongue region becomes a key of automatic tongue diagnosis. However, tongue images segmentation is difficult for some physiological properties: tongue is non-rigid and has a high degree of variability in size, shape, color and texture. This paper presents a novel tongue detection method based on *** this method to tongue image, we can get the satisfying results with the respect to robust and veracity.

关键词： Tongue shape Detection B-Spline

来源：评论

学校读者我要写书评

暂无评论

Detection of small target in infrared image sequences using attention mechanism

Detection of small target in infrared image sequences using ...

引用

Systems and Control in Aerospace and Astronautics, 2006. ISSCAA 2006. 1st International Symposium on

作者： Xun Yao Dehua Li Xianbin Sun Institute of pattern recognition and artificial intelligence Key Laboratory of Education Ministry for Image processing & Intelligence Control Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)0780393953

The requirement of algorithm for detecting small target in infrared image sequences is not only a high rate to identify the true target and a low false alarm rate, but also the computation efficiency. By employing the selective attention mechanism, biological visual system can interpret a complex incoming image in real time with limited hardware resources. Much evidence has suggested that the biological visual system processes information in a serial strategy which rapidly selects a small relevant region in scene for further complex and time consuming analysis. In this paper, a two component computation scheme is proposed to detect dim targets in infrared image sequences. In the first process stage, an efficient method is applied to extract the potential targets which are further identified in second phase, the true targets are detected, and the spurious objects are rejected. The attention-based approach reduces the computation complexity, while the other performance aspects are not traded off. Experimental results indicate that the proposed extraction and recognition modules exhibit excellent performance of detecting small target in infrared image sequences, especially in process speed aspect.

关键词： feature extraction image sequences infrared imaging biological visual system computation complexity computation efficiency false alarm rate feature extraction image recognition modules infrared image sequences selective attention mechanism small target d

来源：评论

学校读者我要写书评

暂无评论

A Velocity-Separation Difference Model for Car-Following Theory and Simulation Tests

A Velocity-Separation Difference Model for Car-Following The...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Zhipeng Li Xiaobo Gong Yuncai Liu Institute of Image Processing Pattern Recognition Shanghai JiaoTong University Shanghai China Department of Control Science and Technology Shanghai JiaoTong University Shanghai China

This paper attempts to introduce a velocity-separation difference model that modifies the previous models in the literature. The improvement of this new model over the previous ones lies in that it performs more realistically than others in the dynamical evolution of congestion. Furthermore, the proposed model is investigated with analytic and numerical method, with the finding that this model can demonstrate some complex physical features observed in real traffic such as the existence of three phases: free flow, coexisting flow, and jam flow; sudden flow drop; traffic hysteresis in transition between the free and the coexisting flow

关键词： Testing Traffic control Telecommunication traffic Road vehicles Mathematical model Intelligent transportation systems Acceleration Hysteresis Computer networks Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Fractal Volume Rendering

Fractal Volume Rendering

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Xiaoliang Li Hongxing Qin Jie Yang Yuemin Zhu Institute of Image Processing & Pattern Recognition Shanghai Jiaotong University Shanghai China Research unit 5515 & Inserm unit 630 CREATIS/CNRS Villeurbanne France

Efficient visualization of large volumetric data is a challenge for image processing community. In this paper, we present a novel volume rendering algorithm based on the concept of fractal. It consists of dividing the volumetric data set into sub-blocks, calculating the 3D fractal coefficients of each sub-block, projecting them to 2D image plane, and generating sub-images through 2D inverse fractal transform. The final rendered image is then obtained by simply summing the sub-images. Compared to the conventional ray casting technique, the proposed fractal volume rendering (FVR) method presents the advantage of reducing time complexity as well as memory complexity while maintaining good rendering quality. Moreover, the progressive refinement is supported owing to the iterative convergent process of sub-image generation

关键词： Fractals Rendering (computer graphics) Data visualization image generation Casting image processing image converters Computed tomography Magnetic resonance imaging Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

image Indexing Using Weighted Color Co-occurrence Matrix and Feature Selection

Image Indexing Using Weighted Color Co-occurrence Matrix and...

引用

IEEE Region 10 International Conference TENCON

作者： Dong Liang Edmund Y. Lam Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong China Institute of Image Processing and Pattern Recognition Shanghai JiaoTong University Shanghai China

In this paper, image indexing based on weighted color co-occurrence matrix (WCCM) feature and isolation parameter-based feature selection is introduced. In this method, isolation parameter (IP) is used to indicate the visual perception complexity and conduct feature selection for each query image. When indexing images from database in the reduced feature space, the similarities of diagonal elements and non-diagonal elements of CCM feature are weighted separately with different values based on the isolation parameters of query image and images from database. The experiments show that the proposed method provides better results than modified color co-occurrence matrix (MCCM) based method and sub-range cumulative histogram (SCH) based method

关键词： Indexing image databases Spatial databases image retrieval Visual databases Frequency Color Visual perception image processing pattern recognition

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：