检索结果-内蒙古大学图书馆

2012 ACM Symposium on Document Engineering, DocEng 2012

作者： Gabdulkhakova, Aysylu Hassan, Tamir Department of Computing Mathematics and Cybernetics Ufa State Aviation Technical University K. Marx str. 12 450000 Ufa Russia Pattern Recognition and Image Processing Group Technische Universität Wien Favoritenstraße 9-11 1040 Wien Austria

ISBN: (纸本)9781450311168

This paper presents an object-based method for analysing the content drawn by graphical operators in natively digital PDF documents. We propose that graphical content in a document can be classified either as structural or nonstructural and present an output model for our analysis result. Heuristic techniques are used to group the instructions into regions and determine their logical role in the document's structure. Experimental results demonstrate the effectiveness of the algorithm. Copyright © 2012 by the Association for Computing Machinery, Inc. (ACM).

关键词： Structural analysis

来源：评论

学校读者我要写书评

暂无评论

Combining shape from silhouette and shape from structured light for volume estimation of archaeological vessels

Proceedings - International Conference on Pattern Recognitio...

引用

Proceedings - International Conference on pattern recognition 2002年第1期16卷 364-367页

作者： Sablatnig, Robert Tosovic, Srdan Kampel, Martin Vienna University of Technology Institute of Computer Aided Automation Pattern Recognition and Image Processing Group Favoritenstr. 9 183-2 A-1040 Vienna Austria

An algorithm for the automatic construction of a 3d model of archaeological vessels using two different 3d algorithms is presented. In archeology the determination of the exact volume of arbitrary vessels is of importance since this provides information about the manufacturer and the usage of the vessel. To acquire the 3d shape of objects with handles is complicated, since occlusions of the object's surface are introduced by the handle and can only be resolved by taking multiple views. Therefore, the 3d reconstruction is based on a sequence of images of the object taken from different viewpoints with two different algorithms;shape from silhouette and shape from structured light. The output of both algorithms are then used to construct a single 3d model. Results of the algorithm developed are presented for both synthetic and real input images. © 2002 IEEE.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Robust spot fitting for genetic spot array images

Robust spot fitting for genetic spot array images

引用

IEEE International Conference on image processing

作者： H.-Y. Chen N. Brandle H. Bischof H. Lapp Pattern Recognition & Image Processing Group University of Technology Vienna Vienna Austria Novartis Research Institute Vienna Genetics Vienna Austria

Addresses the problem of reliably fitting parametric and semi-parametric models to high density spot array images obtained in gene expression experiments. The goal is to measure the amount of genetic material at specific spot locations. Many spots can be modelled accurately by a Gaussian shape. In order to deal with highly overlapping spots the authors use robust M-estimators. When the parametric method fails, they use a novel, robust semi-parametric method which can handle spots of different shapes accurately. They present the results for real data and compare the complexity of the two methods.

关键词： Robustness Genetics Shape image analysis Gene expression pattern recognition image processing Lapping Safety Noise shaping

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Tracking Based on Colour and Spatial Information

Pedestrian Tracking Based on Colour and Spatial Information

引用

Proceedings of the Digital image Computing: Technqiues and Applications (DICTA)

作者： F.H. Seitner B.C. Lovell Pattern Recognition and Image Processing Group University of Technology Vienna Austria National ICT Australia and School of ITEE University of Queensland Australia

This paper describes a tracking with appearance modelling system for pedestrians. A cascade of boosted classifiers and Haar-like rectangular features [6, 12] are used for the pedestrian detection. Statistical modelling in the HSV colour space is used for adaptive background modelling and subtraction, where the use of circular statistics for hue is proposed. By using the background model in combination with the detector, the system extracts a feature vector based on colour statistics and the spatial information. Circular [9] and linear statistics are applied on the extracted features to robustly track the pedestrians and other moving objects through the scene. An adaptive appearance model copes with partial or full occlusions and addresses the problem of missing or wrong detections in single frames.

关键词： Statistics Data mining Feature extraction image color analysis Detectors pattern recognition image processing Australia Vectors Robustness

来源：评论

学校读者我要写书评

暂无评论

Ancient coins & ceramics - 3d and 2d documentation for preservation and retrieval of lost heritage 2

Ancient coins & ceramics - 3d and 2d documentation for prese...

引用

2nd ISPRS International Workshop on Virtual Reconstruction and Visualization of Complex Architectures, 3D-ARCH 2007

作者： Mara, Hubert Kampel, Martin Niccolucci, Franco Sablatnig, Robert PIN - Servizi Didattici e Scientifici Universit di Firenze VAST-Laboratory Piazza Ciardi 25 Prato59100 Italy Vienna University of Technology Institute for Computer Aided Automation Pattern Recognition Image Processing Group Favoritenstrasse 9/183-2 Vienna1040 Austria

Motivated by the requirements of archaeologists we are developing an automated system for acquisition, documentation and management of daily finds of excavations. These daily finds can be separated into large objects like remainders of architecture and small objects of ancient daily life - like ceramics and coins. Ceramics especially are found in numbers of tens of thousands on virtually every excavation, because ceramics have been in use for thousands of years. Until the present day these finds are documented by manual drawings. There is a similar situation in the case of coins, where manual drawings are often used to abstract them from photographs. Therefore we propose an automated acquisition and documentation system based on digital cameras and structured light for small findings. For ceramics we provide further processing to estimate horizontal cross-sections (profile-lines) for printed documentation, as it is done by manual drawing. For this a proper orientation of the acquired 3D-model is required and automatically estimated based on the assumption that ceramics were made on rotational plates (wheels). We are aware that ceramics might not always have been manufactured on rotational plates, because the wheel was not invented everywhere as for the example in the Americas. Even though ceramics from such areas appear to be rotational symmetric, we developed a method based on shape and symmetry analysis to determine the manufacturing techniques of ceramics. This helps to answer another archaeological question regarding the technological advance of an ancient culture. Results for accuracy and performance are shown on real data from recent interdisciplinary projects together with archaeologists from Austria, Germany, Israel and Peru. Furthermore we present preliminary results of the integration of coin classification in our documentation system. Additionally we are currently adapting the London Charter to ensure the intellectual integrity, reliability, transparency,

关键词： Excavation

来源：评论

学校读者我要写书评

暂无评论

Logarithmic tapering graph pyramid

Logarithmic tapering graph pyramid

引用

24th German Association for pattern recognition Symposium, DAGM 2002

作者： Haxhimusa, Yll Glantz, Roland Saib, Maamar Langs, Georg Kropatsch, Walter G. Pattern Recognition and Image Processing Group 183/2 Institute for Computer Aided Automation Vienna University of Technology Favoritenstrasse 9 ViennaA-1040 Austria Dipartimento di Informatica Università di Ca’ Foscari di Venezia Via Torino 155 MestreVE30172 Italy

ISBN: (纸本)354044209X

We present a new method to determine contraction kernels for the construction of graph pyramids. The new method works with undirected graphs and yields a reduction factor of at least 2.0. This means that with our method the number of vertices in the subgraph induced by any set of contractible edges is reduced to half or less by a single parallel contraction. Our method yields better reduction factors than the stochastic decimation algorithm, in all tests. The lower bound of the reduction factor becomes crucial with large images. © Springer-Verlag Berlin Heidelberg 2002.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Registration and enhancing of multispectral manuscript images

Registration and enhancing of multispectral manuscript image...

引用

European Signal processing Conference (EUSIPCO)

作者： Martin Lettner Markus Diem Robert Sablatnig Heinz Miklas Pattern Recognition and Image Processing Group Vienna University of Technology Vienna Austria Institute for Slavonic Studies University of Vienna Vienna Austria

Two medieval manuscripts are recorded, investigated and analyzed by philologists in collaboration with computer scientists. Due to mold, air humidity and water the parchment is partially damaged and consequently hard to read. In order to enhance the readability of the text, the manuscript pages are imaged in different spectral bands ranging from 360 to 1000nm. A registration process is necessary for further image processing methods which combine the information gained by the different spectral bands. Therefore, the images are coarsely aligned using rotationally invariant features and an affine transformation. Afterwards, the similarity of the different images is computed by means of the normalized cross correlation. Finally, the images are accurately mapped to each other by the local weighted mean transformation. The algorithms used for the registration and results in enhancing the texts using Multivariate Spatial Correlation are presented in this paper.

关键词： Correlation Principal component analysis Remote sensing Cameras Eigenvalues and eigenfunctions Europe Signal processing

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

Fuzzy c-means in an MDL-framework

Fuzzy c-means in an MDL-framework

引用

International Conference on pattern recognition

作者： A. Selb H. Bischof A. Leonardis Pattern Recognition and Image Processing Group University of Technology Vienna Vienna Austria Faculty of Computer and Information Science University of Ljubljana Ljubljana Slovenia

ISBN: (纸本)0769507506

In this paper we present a minimum description length (MDL) framework for fuzzy clustering algorithms. This framework enables us to find an optimal number of cluster centers. We applied our approach to the fuzzy c-means algorithm for which we designed a computationally efficient procedure. We report the results of our approach on a 2D clustering problem and on RGB color image segmentation.

关键词： Clustering algorithms Radial basis function networks Encoding Color image segmentation image recognition image processing Algorithm design and analysis Unsupervised learning pattern recognition

来源：评论

学校读者我要写书评

暂无评论

On ancient coin classification

On ancient coin classification

引用

8th International Symposium on Virtual Reality, Archaeology, and Intelligent Cultural Heritage, VAST 2007

作者： Zaharieva, M. Huber-Mörk, R. Nölle, M. Kampel, M. TU Vienna Institute for Computer Aided Automation Pattern Recognition and Image Processing Group Favoritenstr. 9/183-2 A-1040 Vienna Austria ARC Seibersdorf Research GmbH Smart Systems Division High Performance Image Processing A-2444 Seibersdorf Austria ARC Seibersdorf Research GmbH Smart Systems Division Quantum Technologies A-2444 Seibersdorf Austria

ISBN: (纸本)9783905674019

Illegal trade and theft of coins appears to be a major part of the illegal antiques market. image based recognition of coins could substantially contribute to fight against it. Central component in the permanent identification and traceability of coins is the underlying classification and identification technology. The first step of a computer aided system is the segmentation of the coin in the image. Next, a feature extraction process measures the coin in order to describe the coin unambiguously. In this paper, we focus on the segmentation task, followed by a comparison of features relevant for coin classification. Results of the algorithms implemented are presented for an image database of ancient coins. © The Eurographics Association 2007.

关键词： image segmentation

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：