检索结果-内蒙古大学图书馆

International Conference on Multimedia Technology

作者： Lie Kang Sheng Zhong Fang Wang State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781612847719

This paper presents a novel fast single-pass contour tracing algorithm in a binary image. The proposed algorithm is viewed as follow steps: firstly a set of contour segments of all object contours can be generated and traced in a top-down line scan fashion; then all contour segments are employed to be integrated into respective intact contours; finally all results are converted into the chain code as the final output. This algorithm can extract multiple contours of an image in one pass and never lose any outer and inner contour of object region. It is faster on implementation. Experiments results prove those advantages.

关键词： Algorithm design and analysis Image segmentation Signal processing algorithms Shape Labeling Lakes pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A novel method concerning about image transition region extraction and segmentation

A novel method concerning about image transition region extr...

引用

International Conference on Multimedia Technology

作者： Fang Wang Tianxu Zhang Jinpeng Deng State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

According to the feature that the gray distribution of the transition region (locating between the objects and the background) is more scattered than that of the regions of targets or background in an image, this paper proposes a novel method concerning about transition region extraction and segmentation, which is based on local variance of different areas of an image. The experiments indicate that the proposed approach can achieve better segmentation results than the local complexity method (one of the previous methods for extracting transition region).What's more, the novel approach outperforms the local complexity method about more complete and more accurate transition regions, less interference from backgrounds, more detail information of segmented targets, clearer and better segmented targets, easier calculation, and higher processing speed.

关键词： Image segmentation Complexity theory Feature extraction Histograms Data mining Image edge detection Gray-scale

来源：评论

学校读者我要写书评

暂无评论

Weakly supervised locality sensitive hashing for duplicate image retrieval

Weakly supervised locality sensitive hashing for duplicate i...

引用

IEEE International Conference on Image processing

作者： Yudong Cao Honggang Zhang Jun Guo Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications China College of Electronics and Information Engineering Liaoning University of Technology Jinzhou China

Locality sensitive hashing (LSH) is quite popular in high dimensional data indexing. However, most of existing methods perform hashing in an unsupervised way, that is to say, hash functions are randomly generated without the prior information of the data. In this paper, we propose two improved LSH algorithms based on weakly supervised learning technique, which need only small quantities of labeled sample pairs. One is to select the most appropriate hash functions from a pool of functions using sample pairs labeled with “similar” or “dissimilar”. The other is to generate hash functions with positive sample pairs. The experiments show that the proposed algorithms reduce the search complexity compared with original LSH.

关键词： Vectors Accuracy Image retrieval Measurement Data structures Educational institutions Conferences

来源：评论

学校读者我要写书评

暂无评论

Overview of approaches for accelerating scale invariant feature detection algorithm

Overview of approaches for accelerating scale invariant feat...

引用

International Conference on Electric information and Control Engineering (ICEICE)

作者： Jing zhang Hongshi Sang Xubang Shen National Key Laboratory of Science and Technology on Multi-spectral Information Processing Institute for Pattern Recognition & Artificial Intelligence Huazhong University of Science and Technology Wuhan China

SIFT (Scale Invariant Feature Transform) is one of most popular approach for feature detection and matching. Many parallelized algorithms have been proposed to accelerate SIFT to apply into real-time systems. This paper divides the researches into three different categories, that is, optimizing parallel algorithms based on general purpose multi-core processors, designing customized multi-core processor dedicated for SIFT and implementing SIFT based FPGA (Field Programmable Gate Arrays). Overview of the three type researches and analysis of task-level parallelism are presented in this paper.

关键词： Feature extraction Pixel Multicore processing Parallel algorithms Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Selection of optimal wavelet basis for singularity detection of non-stationary signal

Selection of optimal wavelet basis for singularity detection...

引用

International Conference on Electrical and Control Engineering (ICECE)

作者： Licheng Xu Misheng Xue Institute for Pattern Recognition and Artificial Intelligence State key Laboratory for Multi-spectral Information Processing Technology Huazhong University of Science and Technology Wuhan Hubei China

By using wavelet transform modulus maximum principle for non-stationary signal singularity detection is a kind of very good method. Through to the various wavelet singularity extracted, the analysis results can be divided into four types: accurate location, the approximate location, overlapping effect, rim effect. According to the classification we learn the optimal wavelet basis should has the following features: the optimum wavelet basis should have strong ability of detecting and precision, and at the same time the influence of overlap and rim should be as small as possible. According to these characteristics, a discriminant function is constructed. The wavelet basis makes the largest discriminant function value is optimal. The experimental results show that the method in this paper according to find out the optimum wavelet basis did more than other wavelet detection effect better.

关键词： Wavelet transforms Wavelet analysis Educational institutions information processing pattern recognition Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Double-Row Cascade Labeling Algorithm for Hyper-Scale Issue

引用

Procedia Engineering 2011年 15卷 4047-4051页

作者： Yebin Fan Hualong Zhao Department of Computer Science Huazhong University of Science and Technology National Key Laboratory of Science and Technology on Multi-Spectral Information Processing Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology

An efficient algorithm is presented to label the connected components in the case that the primary memory is smaller than the image data. Our algorithm uses only the memory of two image rows to label the huge image or any image larger than the available memory. The search path compression is a applied for improving the performance further. An extensive comparison with the state-of-art algorithms is proposed, both on random and real datasets. Our algorithm shows an impressive speedup, while the auxiliary memory is not required at all comparing with all competitors.

关键词： Connected components labeling page fault hyper-scalar union-find

来源：评论

学校读者我要写书评

暂无评论

Selection of optimal wavelet basis for singularity detection of non-stationary signal

Selection of optimal wavelet basis for singularity detection...

引用

2nd Annual Conference on Electrical and Control Engineering, ICECE 2011

作者： Xu, Licheng Xue, Misheng Huazhong University of Science and Technology Institute for Pattern Recognition and Artificial Intelligence State Key Laboratory for Multi-spectral Information Processing Technology Wuhan 430074 Hubei China

ISBN: (纸本)9781424481637

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Research on Large-Scale Scene Infrared Simulation Based on Image Classification

Research on Large-Scale Scene Infrared Simulation Based on I...

引用

International Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping

作者： Lamei Zou Tianxu Zhang Wei Lv Guoqing Ao Institute of Pattern Recognition and Artificial Intelligence National key laboratory of science and technology on multi-spectral information processing technologies Huazhong University of Science and Technology Wuhan China

Vega has been widely used in Virtual Reality (VR) field. Vega infrared (IR) module can implement IR simulation, but Vega IR imaging simulation's general approach does not apply to large-scale scene's infrared simulation problem. This article deeps into large-scale scene IR image simulation through Vega infrared module based on visible image, the scene's corresponding Digital Elevation Model (DEM) data and targets' 3D model. A real time large-scale IR simulation system is successfully designed and realized in this paper. At the aspect of image classification, a coarse to fine k-means clustering method based on the consistency of image color is proposed. The proposed automatic texture material mapping method based on the development of Vega TMM tool provides a fast and convenient way for large-scale scene's IR simulation based on Vega IR module. And finally, results of the large-scale scene infrared simulation show the effectiveness of this method.

关键词： Solid modeling Image color analysis Materials Atmospheric modeling Image classification Three dimensional displays Pixel

来源：评论

学校读者我要写书评

暂无评论

An effective document image deblurring algorithm

An effective document image deblurring algorithm

引用

Conference on Computer Vision and pattern recognition (CVPR)

作者： Xiaogang Chen Xiangjian He Jie Yang Qiang Wu Key Laboratory of System Control and Information Processing Ministry of Education China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University China Centre of Innovation in IT Services and Applications University of Technology Sydney Australia

Deblurring camera-based document image is an important task in digital document processing, since it can improve both the accuracy of optical character recognition systems and the visual quality of document images. Traditional deblurring algorithms have been proposed to work for natural-scene images. However the natural-scene images are not consistent with document images. In this paper, the distinct characteristics of document images are investigated. We propose a content-aware prior for document image deblurring. It is based on document image foreground segmentation. Besides, an upper-bound constraint combined with total variation based method is proposed to suppress the rings in the deblurred image. Comparing with the traditional general purpose deblurring methods, the proposed deblurring algorithm can produce more pleasing results on document images. Encouraging experimental results demonstrate the efficacy of the proposed method.

关键词： Image restoration Histograms TV Object segmentation Deconvolution Estimation Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A novel image distance based on high-order manifold approximation

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content Technology and its Applications 2011年第11期5卷 126-133页

作者： Zhou, Hua Ding, Mingyue Cai, Chao The Institute for Pattern Recognition and Artificial Intelligence National Key Laboratory of Science and Technology on Multi-spectral Information Processing Huazhong University of Science and Technology China School of Life Science and Technology Key Laboratory of Education Ministry for Imaging Processing and Intelligence Control Huazhong University of Science and Technology China

Tangent distance measures image similarity in a manifold way and is specific for handwritten digit recognition. However, in tangent distance metric the transformation should be known a priori and nonlinear manifolds are only approximated by first-order tangent hyperplanes. We propose a new image distance metric - the high-order approximated manifold distance (HMD) which can overcome these defects. The intrinsic variables of image transformation are learned by a special manifold learning algorithm - Maximum Variance Unfolding (MVU). Then nonlinear manifold is approximated by curve surface based on higher-order Taylor expansion with respect to intrinsic variables. HMD is defined as the minimum distance between the approximated curved surfaces of manifolds, and can be directly utilized in distance-based classifiers for image recognition. A series of face recognition and handwritten digit recognition experiments demonstrate that HMD not only achieves higher recognition accuracy but also has more stability of classification than several state-of-the-art distance metrics.

关键词： Face 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：