检索结果-内蒙古大学图书馆

INCREASING THE FEATURE SIZE IN HANDWRITTEN NUMERAL RECOGNITION TO IMPROVE ACCURACY

SYSTEMS AND computerS IN JAPAN 1995年第8期26卷 35-44页

作者： WAKABAYASHI, T TSURUOKA, S KIMURA, F MIYAKE, Y Member Faculty of Engineering Mie University Tsu Japan 514 Furnitaka Kimura:received his B.E. and Ph.D. degrees in 1973 and 1978 respectively from Nagoya University where he was appointed a Research Associate the same year. He has been an Associate Professor at Mie University since 1983. He had been a Visiting Associate Professor at the University of Michigan Dearborn from 1989 to 1991. He has engaged in research on pattern recognition image processing computer graphics. He is a member of Institute of Information Processing Japan Institute of Medical Engineering Japan and Institute of Artificial Intelligence Japan. Members Yasuji Miyab:received his B.E. and Ph.D. degrees in 1957 and 1965 respectively from Nagoya University where he was appointed a Research Associate in 1965. He was appointed to a Lecturer in 1968 and an Associate Professor in 1969. He has been a Professor at Mie University since 1978. He has engaged in research on machine recognition of handwritten characters computer graphics and medical image processing. He is a member of Institute of Information Processing Japan Institute of Artificial Intelligence Japan Institute of Robotics Japan I.E.E.E. Japan and Institute of Simulation Japan.

The relationship between the recognition rate of handwritten numerals and the normality of the distribution of their features has been investigated experimentally with a large amount of data in various combinations of quantized orientations and regions. The recognition method is based on the histogram of local orientation of contours of each numeral. To obtain a more accurate orientation quantization, the effectiveness of the orientation quantization using the gray-scale gradient has also been investigated. The results show that: (1) to increase the dimensionality of features, it is better to increase the number of quantized orientations, keeping the number of regions small (e.g., 4 x 4 or 5 x 5);(2) in the same dimensionality, the better the normality of a feature distribution, the higher the recognition rate;(3) a quantization of orientations using gray scales is effective for normalizing a feature distribution;and (4) the filter processing in reduction of the number of quantization scales improves the normality and recognition rate. The recognition of handwritten numerals collected from actual posts were carried out by using the gray-scale local-orientation histogram (400 dimensions). A correct recognition rate of 99.18 percent (mean value) has been obtained.

关键词： CHARACTER RECOGNITION PATTERN RECOGNITION ZIP CODE RECOGNITION FEATURE EXTRACTION GRADIENT NORMALITY

来源：评论

学校读者我要写书评

暂无评论

引用

SYSTEMS AND computerS IN JAPAN 1995年第11期26卷 100-109页

作者： WAKIMOTO, K TANAKA, S MAEDA, A SHIMA, M Member Computer and Information Systems Laboratory Mitsubishi Electric Corporation Kamakura Japan 247 Members ALira Maeda:received his M.S. degree in Electrical Engineering from Osaka University and joined Mitsubishi Electric Corporation in 1971. He has been with Information Systems Research Lab. since. He has been working on image information processing systems among others. He is a member of the Information Processing Society. Nonmember

An efficient method to retrieve necessary information from drawings for plant diagrams, logic circuit diagrams, etc. stored in a database is presented. In the image information retrieval systems currently in use, a keyword is assigned to each diagram and information is retrieved by the user by giving the keyword. When the features of the desired image are not registered as a keyword, however, its retrieval becomes difficult. In this paper a method is proposed in which the user shows features of the desired diagram using a sample diagram and a section similar to the sample diagram is retrieved. In this research, diagrams consisting mainly of symbols and connecting lines are considered. This kind of diagram is represented by a graph and similarities in topological features between the sample graph and graph representations of the diagrams in the database are evaluated. The retrieval is then performed based on the value obtained. The results of an experiment conducted using plant diagrams show that similar diagrams can be retrieved using this method.

关键词： image DATABASES MATCHING SIMILARITY RETRIEVAL PLANT DIAGRAMS

来源：评论

学校读者我要写书评

暂无评论

An extended probabilistic collaborative representation based classifier for image classification

An extended probabilistic collaborative representation based...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Rushi Lan Yicong Zhou Key Laboratory of Intelligent Processing of Computer Image and Graphics Guilin University of Electronic Technology Guilin China Department of Computer and Information Science University of Macau Macau China

ISBN: (纸本)9781509060689

Collaborative representation based classifier (CRC) and its probabilistic improvement ProCRC have achieved satisfactory performance in many image classification applications. They, however, do not comprehensively take account of the structure characteristics of the training samples. In this paper, we present an extended probabilistic collaborative representation based classifier (EProCRC) for image classification. Compared with CRC and ProCRC, the proposed EProCRC further considers a prior information that describes the distribution of each class in the training data. This prior information enlarges the margin between different classes to enhance the discriminative capacity of EProCRC. Experiments on two challenging databases, namely CUB200-2011 and Caltech-256, are conducted to evaluate EProCRC, and comparison results demonstrate that it outperforms several state-of-the-art classifiers.

关键词： Training Collaboration Probabilistic logic Training data Feature extraction Databases Robustness

来源：评论

学校读者我要写书评

暂无评论

Technical note: Error analysis of material-decomposition-based effective atomic number quantification method

引用

Medical Physics 2024年第1期51卷 419-427页

作者： Chen, Li Ji, Xu Wang, Zhe Chen, Yang Laboratory of Image Science and Technology the School of Computer Science and Engineering Southeast University Nanjing China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Southeast University Nanjing China Beijing Engineering Research Center of Radiographic Techniques and Equipment Institute of High Energy Physics Chinese Academy of Sciences Beijing China Jinan Laboratory of Applied Nuclear Science Jinan China Ministry of Education China

Background: The effective atomic number (Zeff) is widely applied to the identification of unknown materials. One method to determine the Zeff is material-decomposition-based spectral X-ray imaging. The method relies on certain approximations of the X-ray interaction cross-sections such as empirical model coefficients. The impact of such approximations on the accuracy of Zeff quantification has not been fully investigated. Purpose: To perform an error analysis of the material-decomposition-based Zeff quantification method and propose a coefficient calibration-in-groups method to improve the modeling accuracy and reduce the Zeff quantification error. Methods: The model of the material-decomposition-based Zeff quantification method relies on the dependence of the interaction cross-sections (σPE) on the atomic number Z and corresponding coefficient, that is, (Formula presented.). In this work, all the data is from the National Institute of Standards and Technology (NIST) website. First, the coefficient m is calibrated through a logarithmic fitting method to quickly determine the m values for any certain energy and Zeff ranges. Then materials including elements and common compounds with Zeff ranging from 6–20 are selected as the objects whose effective atomic numbers are to be quantified. Different combinations of basis materials are applied to decompose the object materials and their quantification errors are analyzed. With the help of error analysis, the object materials are divided into high-error and low-error groups based on the decomposition coefficient ratio (Formula presented.), which is found to have a strong correlation with error, and their coefficients are calibrated in groups. Finally, the average errors of three m selection strategies: (1) using an empirical m value of 3.94, which is also considered a standard method;(2) using a single m value, which is calibrated through the logarithmic fitting method;(3) using different m values calibrated in groups, are

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

QR code localization using deep neural networks

QR code localization using deep neural networks

引用

IEEE Workshop on Machine Learning for Signal processing

作者： Tamás Grósz Péter Bodnár László Tóth László G. Nyúl MTA-SZTE Research Group on Artificial Intelligence Hungarian Academy of Sciences and University of Szeged Department of Image Processing and Computer Graphics University of Szeged

Usage of computer-readable visual codes became common in our everyday life at industrial environments and private use. The reading process of visual codes consists of two steps, localization and data decoding. This paper introduces a new method for QR code localization using conventional and deep rectifier neural networks. The structure of the neural networks, regularization, and training parameters, like input vector properties, amount of overlapping at samples, and effect of different block sizes are evaluated and discussed. Results are compared to localization algorithms of the literature.

关键词： Training Vectors Artificial neural networks Neurons Visualization Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

FAST ALGORITHM FOR COMPUTING FRACTAL DIMENSIONS OF image SEGMENTS

FAST ALGORITHM FOR COMPUTING FRACTAL DIMENSIONS OF IMAGE SEG...

引用

SATELLITE CONF AT THE 1988 BIANNUAL INTERNATIONAL CONF ON PATTERN RECOGNITION : RECENT ISSUES IN PATTERN ANALYSIS AND RECOGNITION

作者： CREUTZBURG, R IVANOV, E Central Institute of Cybernetics and Information Processes International Basic Laboratory for Image Processing and Computer Graphics Academy of Sciences of the G.D.R. Kurstr. 33 P. O. Box 1298 Berlin DDR - 1086 Germany Department of Information Techniques University of Technology Mommsenstr. 13 Dresden DDR - 8027 Germany

来源：评论

学校读者我要写书评

暂无评论

Operators to dilate and erode color impulse noise images based on the morphology

Operators to dilate and erode color impulse noise images bas...

引用

International Conference on E-Business and E-Government (ICEE)

作者： Ah Yin Xing-yun Research direction: Digital Image Processing Computer Graphics Computer and Information Engineering Department Huainan Normal University Huainan 232038 P. R. China

By analyzing the numerical characteristics of impulse noise images, in order to resolve spreading-noise problem resulted from dilating and eroding images base on mathematical morphology, an algorithm of dilating and eroding color impulse noise images based on mathematical morphology is proposed. The result of the experiment demonstrates that the new algorithm has same effect as traditional algorithm of dilating and eroding images, but also suppresses impulse noise.

关键词： Niobium image color analysis Morphology computers Colored noise Machine vision

来源：评论

学校读者我要写书评

暂无评论

Colour Adjustment and Specular Removal for Non-uniform Shape from Shading

Colour Adjustment and Specular Removal for Non-uniform Shape...

引用

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

作者： Xiaozheng Zhang Yongsheng Gao Terry Caelli Computer Vision and Image Processing Laboratory Griffith University Australia Biosecurity Group Queensland Research Laboratory NICTA Australia

Surface colour changes and specular reflections are two major problems in 3D modelling using shape-from-shading (SFS). This paper proposes to pre-process the input image for a typical SFS algorithm, so that the resultant image has no colour changes and specular reflection. First, a chromaticity-based specular reflection removal algorithm is applied to achieve a pure diffuse (Lambertian) reflected image. Then, a novel chromaticity-based colour adjustment approach is proposed to generate an image without surface colour changes. The standard SFS algorithms can then be applied successfully onto the processed images to produce plausible 3D models. In experiments, the proposed approach was tested on standard SFS datasets with complex surface colours. The experimental results show it's promising to facilitate SFS algorithms to handle SFS problems with more complex surface properties and illumination conditions.

关键词： image color analysis Reflection Pixel Shape Classification algorithms Surface treatment Lighting

来源：评论

学校读者我要写书评

暂无评论

Width Distributions for Shape Description

Width Distributions for Shape Description

引用

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

作者： Xiaozheng Zhang Yongsheng Gao Biosecurity Group Queensland Research Laboratory NICTA Australia Computer Vision and Image Processing Laboratory Griffith University Australia

Measuring the similarity between articulated shapes is a fundamental yet challenging problem. This paper proposes a novel shape descriptor based on Width Distributions (WD), which is robust to articulations. We show that the width distributions are articulation insensitive yet descriptive to distinguish different shapes with varied part structures. With measurements on distributions only, the proposed method does not require any alignment between two objects and thus is more robust than correspondence-based measurements. First, the medial axes of the objects are extracted and fitted to B-Splines to remove outliners. The width of the object shape perpendicular to the medial axis can be calculated for each position on the medial axis. The histograms of those widths are compared using chi-square method for similarity. Experiments on standard 2D shape database show that the proposed method performed better than standard shape distribution algorithms and similarly to other articulation-robust shape descriptors, such as inner-distance. The speed of the proposed method is much faster than the more sophisticated inner-distance, as the proposed method is much simpler in nature and requires limited image processing and pattern classification. These results suggested it could be an efficient and effective method to describe and to match articulated shapes.

关键词： Shape Histograms Robustness Databases Shape measurement Three dimensional displays Face

来源：评论

学校读者我要写书评

暂无评论

Classification of gothic and baroque architectural elements

Classification of gothic and baroque architectural elements

引用

International Conference on Systems, Signals and image processing, IWSSIP

作者： Gayane Shalunts Yll Haxhimusa Robert Sablatnig Institute of Computer Aided Automation Computer Vision Laboratory University of Technology Vienna Austria Institute of Computer Graphics and Algorithms Pattern Recognition and Image Processing Lab University of Technology Vienna Austria

Architectural elements are the components and details of buildings. Their unique set, combination, design, construction technique form the architectural style of buildings. Building facade classification by architectural styles is viewed as a task of classifying separate architectural structural elements. In the scope of building facade architectural style classification the current paper targets the problem of classification of Gothic and Baroque architectural elements called tracery, pediment and balustrade. Since certain gradient directions dominate on the shape of each architectural element, discrimination between dominating gradients means classification of architectural elements and thus architectural styles. We use local features to describe gradient directions. Our approach is based on clustering and learning of local features and yields a high classification rate.

关键词： Shape Three dimensional displays Visualization computer vision Histograms Windows

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：