检索结果-内蒙古大学图书馆

IEEE International Conference on Fuzzy systems

作者： Gleb Beliakov Gang Li Huy Quan vu Tim Wilkin School of Information Technology Deakin University Australia

Pixel-scale fine details are often lost during image processing tasks such as image reduction and filtering. Block or region based algorithms typically rely on averaging functions to implement the required operation and traditional function choices struggle to preserve small, spatially cohesive clusters of pixels which may be corrupted by noise. This article proposes the construction of fuzzy measures of cluster compactness to account for the spatial organisation of pixels. We present two construction methods (minimum spannning trees and fuzzy measure decomposition) to generate measures with specific properties: monotonicity with respect to cluster size;invariance with respect to translation, reflection and rotation;and, discrimination between pixel sets of fixed cardinality with different spatial arrangements. We apply these measures within a non-monotonic mode-like averaging function used for image reduction and we show that this new function preserves pixel-scale structures better than existing monotonic averages.

关键词： Shape Shape measurement Rotation measurement Noise Context Weight measurement image resolution

来源：评论

学校读者我要写书评

暂无评论

Automatic optic disc detection in digital fundus images using image processing techniques

Automatic optic disc detection in digital fundus images usin...

引用

International Conference on Information Communication and Embedded systems (ICICES)

作者： Snehal B. Akhade v. U. Deshmukh S. B. Deosarkar Department of Electronics and Telecommunication Engineering VPCOE Baramati (University of Pune) Baramati India

Optic disc (OD) is an important part of the eye. In developing systems, automatic OD detection is an important step for automated diagnosis of various serious ophthalmic diseases like Diabetic retinopathy, Glaucoma and hypertension, etc. The variation of intensity within the OD and intensities close to the OD boundary are the major hurdle in automated OD detection. General edge detection algorithms are frequently unsuccessful to segment the OD because of this. Complexity increases due to the presence of blood vessels. This paper presents a simple method for OD segmentation by using techniques like Principal Component Analysis (PCA), Mathematical Morphology and Circular Hough Transform. PCA used for good presentation of the input image and mathematical morphology is used to remove blood vessels from the image. Circular Hough Transform is used for boundary segmentation.

关键词： image segmentation Optical imaging Optical filters Integrated optics Principal component analysis Blood vessels Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Texture image classification based on using descriptor of indexes

Texture image classification based on using descriptor of in...

引用

International Conference on Signal processing Proceedings (ICSP)

作者： A.I. Sherstobitov D.v. Timofeev v.I. Marchuk v.v. voronin v.P. Fedosov Dept. of Radio Electronics Systems Don State Technical University

A texture descriptor based on a set of indices of degrees of local approximating polynomials is proposed in this paper. An image is split into non-overlapping patches, reshaped into one-dimensional source vectors and convolved with the polynomial approximation kernels of various degrees p. As a result, a set of approximations is obtained. For each element of the source vector, these approximations are ranked according to the difference between the original and approximated values. A set of indices of polynomial degrees form a local feature. This procedure is repeated for each pixel from the local area. Finally, a proposed texture descriptor is obtained from the frequency histogram of all obtained local features. A nearest neighbor classifier utilizing correlation distance metric is used to evaluate a performance of the introduced descriptor. An accuracy of texture classification is evaluated on the Brodatz dataset, with respect to different methods of texture analysis and classification. The results of this comparison show that the proposed method is competitive with the recent statistical approaches such as local binary patterns (LBP), local ternary patterns, completed LBP, Weber's local descriptor, and vZ algorithms (vZ-MR8 and vZ-Joint).

关键词： Approximation methods Polynomials Accuracy Databases vectors Kernel Support vector machine classification

来源：评论

学校读者我要写书评

暂无评论

Mapping of mineral deposits using image fusion by PCA approach

Mapping of mineral deposits using image fusion by PCA approa...

引用

International Conference on Computer and Communications Security (ICCCS)

作者： S. Rajalakshmi v. vijaya Chamundeeswari DEPT OF CSE VELAMMAL ENGINEERING COLLEGE Velammal Engineering College Chennai Tamil Nadu IN

Earth Observation using Satellite imagery is a challenging tool for analysis but is proved an effective tool in offering a wide coverage. Satellite imagery is an important economical tool in accessing mineral exploration. Mineral mapping using satellite image processing is a large scale approach to exploit available minerals in the earth's crust. There are various satellite sensors to imply the presence of minerals. Each sensor has its own characteristics. Data fusion is the method of collecting and combining data from multiple sensors. In Geographic information systems, various data are used for spatial decision making. The relation between different set of data can be denoted in matrix format and its properties are used by analysing various algorithms. image fusion is used for combining the significant features which are captured by various image sensors. image sharpening, feature enhancement and image classification can be established using image Fusion algorithms. image fusion can be applied at various levels like decision, feature, and pixel level. Mineral exploration is done on the decision and feature level in GIS. In this paper, Principal component analysis method (PCA) was used for combining multi-source and multi-scale geo-information at pixel level for Hyperion and ALI data. Hybrid image is obtained by combining the values of pixels which is spatially based for different set of images and thus generated image is used for extracting the information or classification. Results obtained in this paper give the distribution which is of spatially based for mineral deposits in the study region with the help of AO-1 Hyperion and ALI data.

关键词： Minerals Principal component analysis Satellites Sensor phenomena and characterization Earth Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Flanking stencil method for the detection of impact craters

Flanking stencil method for the detection of impact craters

引用

International Conference on Information Communication and Embedded systems (ICICES)

作者： R. Krishnan Andhe Dharani Dept. of M.C.A R.V College of Engineering Bangalore India Dept. of M.C.A R.V College of Engineering Bangalore India

Detection of the topographical pattern is a challenging area in the field of astronomy and atmospheric science. An improvement is required, in the existing algorithms for the detection of topographical patterns because of the pattern complexity and detection rate. From the satellite, daily about 500 images are transmitted to ground station with resolution ranging from 5-100 meters. The transmission and processing time is important while considering huge volume of data. This paper deals with a novel framework, the flanking stencil method, over the conventional template matching, which provides a competent reduction in execution time. This lightweight framework can be utilized to eliminate the data, during the time of image acquisition which reduces data transmission time and increase in detection rate by using optimum templates. In this approach, the priority of template image, time reduction for comparison between the input image and template image are considered. The storage of coordinates will be useful, so that the coordinate comparison need not be done again. The same method is used here, for the detection of low and high intensity region with the help of different categories of templates. This algorithm includes transformation generator which generates transformed images based on the priority.

关键词： Generators Pattern matching Moon Correlation Conferences Clocks Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Layered RC circuit with dynamic resistances for background subtraction

Layered RC circuit with dynamic resistances for background s...

引用

Workshops on image processing Theory, Tools and Applications, IPTA

作者： Kareł Mozdřeň Eduard Sojka Radovan Fusek Milan Šurkala VŠB-Technical University of Ostrava FEECS 17. listopadu 15/2172 708 33 Czech Republic VSB-Technical University of Ostrava FEECS Czech Republic

Background subtraction is a widely used technique for moving object extraction from video sequences. This technique is a basic component in many surveillance systems. Numerous methods for background subtraction were developed in recent year, and one of them is the Layered RC circuit for background subtraction. This novel method uses a model of RC circuits for background modeling. We have studied this method, and we have developed an improvement of this method using dynamic resistances in the model. This work introduces the reader to background subtraction, discuses related works, describes basic layered LR circuit model, and our improvement to the method. Then, it provides the reader with experiments and a discussion over the results.

关键词： Integrated circuit modeling Adaptation models Mathematical model video sequences Resistors Resistance Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

SLStudio: Open-source framework for real-time structured light

SLStudio: Open-source framework for real-time structured lig...

引用

Workshops on image processing Theory, Tools and Applications, IPTA

作者： Jakob Wilm Oline v. Olesen Rasmus Larsen Department of Applied Mathematics and Computer Science Technical University of Denmark Lyngby Denmark Department of Clinical Physiology Copenhagen University Hospital Denmark

An open-source framework for real-time structured light is presented. It is called “SLStudio”, and enables real-time capture of metric depth images. The framework is modular, and extensible to support new algorithms for scene encoding/decoding, triangulation, and aquisition hardware. It is the aim that this software makes real-time 3D scene capture more widely accessible and serves as a foundation for new structured light scanners operating in real-time, e.g. 20 depth images per second and more. The use cases for such scanners are plentyfull, however due to the computational constraints, all public implementations so far are limited to offline processing. With “SLStudio”, we are making a platform available which enables researchers from many different fields to build application specific real time 3D scanners. The software is hosted at http://***/~jakw/slstudio.

关键词： Cameras Three-dimensional displays Real-time systems Software Decoding Encoding Calibration

来源：评论

学校读者我要写书评

暂无评论

Enhancing vehicular Safety in Adverse Weather using Computer vision Analysis

Enhancing Vehicular Safety in Adverse Weather using Computer...

引用

IEEE vehicular Technology Conference

作者： Che-Tsung Lin Yu-Chen Lin Long-Tai Chen Yuan-Fang Wang Mechanical and Systems Research Laboratories Industrial Technology Research institute Department of Automatic Control Engineering Feng Chia University Department of Computer Science University of California

ISBN: (纸本)9781479944484

The goal of the project is to design intelligent and robust image-processing and augmented-reality algorithms for driver assistance and enhanced vehicular safety. In particular, the focuses were two-fold: (1) realizing the abilities to identify and localize in a vehicle's on-board video the sweeping windshield wipers during raining days and (2) designing and implementing an in-painting technique to remove the image of the windshield wipers and replace it with the corresponding pixels (not blocked by the wipers) from an adjacent video frame.

关键词： Training vehicles vectors Shape Automotive components Roads image color analysis

来源：评论

学校读者我要写书评

暂无评论

A On-line Coherence Identifying Method Based on Independent Component Analysis

A On-line Coherence Identifying Method Based on Independent ...

引用

International Congress on image and Signal processing

作者： Jing Wang Ke Guo Sch. of Electr. Eng. Wuhan Univ. Wuhan China

ISBN: (纸本)9781479958368

For the large interconnected power system, dynamic equivalence could significantly reduce the computing load and manifest the dominant characteristics. Coherent method is one approach of dynamic equivalence and its core is the automatic identification of coherency. Based on the angle perturbed trajectory measured by WAMS, a new coherency recognition method based on Independent Component Analysis is proposed in this paper, which can take advantage of different fault types and the dynamic behavior of nonlinear systems varying characteristics into account. First of all, the power angle collected by WAMS were centralized and whiten and then the angle perturbed trajectory feature was obtained by the FastICA algorithm and the coherent generator groups were identified consequently. This method avoids building of the system model, determining of the system parameters and the model of system operation. The simulations of New England 39-bus system prove the validity of the proposed method. It could give the clustering results accurately.

关键词： independent component analysis power system faults power system interconnection power system measurement FastICA algorithm New England 39-bus system WAMS angle perturbed trajectory feature angle perturbed trajectory measurement automatic coherency identification coherency recognition method computing load reduction dominant characteristics manifestation dynamic equivalence fault types feature extraction interconnected power system nonlinear systems varying characteristics online coherence identifying method system parameter determination Clustering algorithms Generators Independent component analysis Nonlinear dynamical systems Power system dynamics Power system stability Trajectory coherent recognition

来源：评论

学校读者我要写书评

暂无评论

Use of wavelet for image processing in smart cameras with low hardware resources

引用

JOURNAL OF systems ARCHITECTURE 2013年第10期59卷 826-832页

作者： Courroux, Sebastien Chevobbe, Stephane Darouich, Mehdi Paindavoine, Michel CEA Saclay Nano INNOV LIST CEA F-91191 Gif Sur Yvette France Univ Bourgogne LEAD Lab F-21000 Dijon France

images from embedded sensors need digital processing to recover high-quality images and to extract features of a scene. Depending on the properties of the sensor and on the application, the designer fits together different algorithms to process images. In the context of embedded devices, the hardware supporting those applications is very constrained in terms of power consumption and silicon area. Thus, the algorithms have to be compliant with the embedded specifications i.e. reduced computational complexity and low memory requirements. We investigate the opportunity to use the wavelet representation to perform good quality image processing algorithms at a lower computational complexity than using the spatial representation. To reproduce such conditions, demosaicing, denoising, contrast correction and classification algorithms are executed over several well known embedded cores (Leon3, Cortex A9 and DSP C6x). Wavelet-based image reconstruction shows higher image quality and lower computational complexity (3x) than usual spatial reconstruction. The use of wavelet decomposition also permits to increase the recognition rate of faces while decreasing computational complexity by a factor 25. (C) 2013 Elsevier B.v. All rights reserved.

关键词： Wavelet DWT Demosaicing Denoising Recognition Embedded systems

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：