检索结果-内蒙古大学图书馆

Document Recognition and Retrieval XVI

作者： Zhang, Yu Liu, Changsong Ding, Xiaoqing Wang, Kongqiao State Key Laboratory of Intelligent Technology and Systems Dept. of Electronic Engineering Tsinghua University Beijing 100084 China System Research Center Nokia Research Center Beijing China

In camera-based optical character recognition (OCR) applications, warping is a primary problem. Warped document images should be restored before they are recognized by traditional OCR algorithm. This paper presents a novel restoration approach, which first makes an estimation of baseline and vertical direction estimation based on rough line and character segmentation, then selects several key points and determines their restoration mapping as a result of the estimation step, at last performs Thin-Plate Splines (TPS) interpolation on full page image using these key points mapping. The restored document image is expected to have straight baselines and erect character direction. This method can restore arbitrary local warping as well as keep the restoration result natural and smooth, consequently improves the performance of the OCR application. Experiments on several camera captured warped document images show effectiveness of this approach. © 2009 SPIE-IS&T.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

A machine learning technique to detect and predict parkinson's disease

A machine learning technique to detect and predict parkinson...

引用

2009 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2009

作者： Yuan, Peijiang Zhang, Bo Li, Jianmin Wang, Julei Gao, Guodong State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing 100084 China TangDu Hospital Institute of Functional Brain Disorders Fourth Military Medical University Xi'an China

ISBN: (纸本)9781601321190

Parkinson's Disease (PD) is a neurological disorder that has been a hot topic worldwide. Human neurological disorders can be modeled in animals like rats and monkeys using standardized procedures that recreate specific pathogenic events and their behavioral outcomes. Different methods have been proposed to detect and verify the efficiency and effectiveness of such models. However, the inner scheme to detect and predict PD at the early stage is still a difficult problem. In this paper, a Conditional Random Fields (CRFs) based approach for PD image detection and prediction is presented. Machine learning techniques are discussed that proved to be useful in detecting and predicting PD in animal models.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

PSF-constraints based iterative blind deconvolution method for image deblurring

PSF-constraints based iterative blind deconvolution method f...

引用

16th International Multimedia Modeling Conference on Advances in Multimedia Modeling, MMM 2010

作者： Mo, Xuan Jiao, Jun Shen, Chen Department of Automation State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing China Dept. of Computer Science and Technology Nanjing University Nanjing China School of Software and Electronics Peking University Beijing China

ISBN: (纸本)3642113001

In recent years, Image Deblurring techniques have played an essential role in the field of Image Processing. In image deblurring, there are several kinds of blurred image such as motion blur, defocused blur and gaussian blur. Many methods to address this problem have been proposed by researchers in previous research, among which the iterative blind deconvolution (IBD) method is the most popular method to solve this problem. However, the convergence of this method is not ensured, and there is no effective method to choose a proper initial estimate image and PSF(point spread function). In this paper, we improve the iterative blind deconvolution method by adding several constraints, which could be the type or parameters range of the PSF, on the PSF in each iteration. Experiment results validate that, with the help of these newly added constraints, our method are more likely to converge and has better deblurring performance than the IBD. © 2010 Springer-Verlag Berlin Heidelberg.

关键词： Optical transfer function

来源：评论

学校读者我要写书评

暂无评论

Perfect Distinguishability of Quantum Operations

引用

Physical Review Letters 2009年第21期103卷 210501-210501页

作者： Runyao Duan Yuan Feng Mingsheng Ying State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing 100084 China and Centre for Quantum Computation and Intelligent Systems (QCIS) Faculty of Engineering and Information Technology University of Technology Sydney New South Wales 2007 Australia

We provide a feasible necessary and sufficient condition for when an unknown quantum operation (quantum device) secretly selected from a set of known quantum operations can be identified perfectly within a finite number of queries, and thus complete the characterization of the perfect distinguishability of quantum operations. We further design an optimal protocol which can achieve the perfect discrimination between two quantum operations by a minimal number of queries. Interestingly, we find that an optimal perfect discrimination between two isometries is always achievable without auxiliary systems or entanglement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vision System for an Unmanned Helicopter Landing in Complex Environment

Vision System for an Unmanned Helicopter Landing in Complex ...

引用

Congress on Image and Signal Processing, CISP

作者： Guanlin Wang Haiqing Shi Hong Wang Jihong Zhu State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China

This paper presents a vision-based navigation algorithm for an autonomous helicopter landing in complex environment include appointed landing mark coupled with several similar targets. The vision navigation system is integrated with algorithms of vision detection, target recognition and navigation instruction calculation. The navigation is used for indicating the helicopter to land on the landing mark exactly. In our algorithm, we use international standard landing mark as helicopter landing signal. The experiments results demonstrate that the algorithm has feature of robustness, accuracy and realtime. It meets the actual flight requirements well.

关键词： Machine vision Helicopters Aircraft navigation Computer vision Target recognition Unmanned aerial vehicles Robustness Paper technology Signal design Robots

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised particle filter for visual tracking

Semi-supervised particle filter for visual tracking

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Huaping Liu Fuchun Sun Department of Computer Science and Technology State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing China

In this paper, a semi-supervised particle filter approach is proposed for visual tracking. The combination of semi-supervised learning and particle filter is very natural since the unlabelled samples are generated by particle propagation. In addition, the proposed semi-supervised particle filter can online select different features for robust tracking. To the best knowledge of the authors, this is the first time for the semi-supervised learning technology to be incorporated into the framework of particle filter. Finally, the performance of the proposed approach is evaluated using real visual tracking examples.

关键词： Particle filters Particle tracking Semisupervised learning Robotics and automation Target tracking Boosting Sun Robustness Human robot interaction Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Two Novel Kernel-Based Semi-Supervised Clustering Methods by Seeding

Two Novel Kernel-Based Semi-Supervised Clustering Methods by...

引用

Chinese Conference on Pattern Recognition (CCPR)

作者： Lei Gu Fuchun Sun State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China

Semi-supervised clustering takes advantage of a small amount of labeled data to bring a great benefit to the clustering of unlabeled data. Based on a novel kernel method for clustering using one-class support vector machine, this paper presents two novel kernel-based semi-supervised clustering methods inspired by two semi-supervised variants of the k-means clustering algorithm by seeding respectively. To investigate the effectiveness of our approaches, experiments are done on three real datasets. Experimental results show that the proposed methods can improve the clustering performance significantly compared to other unsupervised and semi-supervised clustering algorithms.

关键词： Clustering methods Clustering algorithms Support vector machines Kernel Iterative algorithms Partitioning algorithms Sun Laboratories intelligent systems Computer science

来源：评论

学校读者我要写书评

暂无评论

Theory and application of image neighborhood parallel processing

Theory and application of image neighborhood parallel proces...

引用

IEEE International Conference on Image Processing

作者： Guangda Su Jiongxin Liu Yan Shang Boya Chen Shi Chen State Key Laboratory of Intelligent Technology and Systems Department of Electronic Engineering Tsinghua University Beijing China

We propose the theory of image neighborhood processing which includes algorithm, storage and processing for parallel image data. Its core idea lies in the identity and parallelism of data structures used by software algorithm, memory and processing unit. This theory solves the problem of frame data flow which is the bottleneck of high speed image processing. In this paper, we discuss the storage structure using incomplete rotate matrix and its corresponding processing unit. Based on the theory of image neighborhood processing, we have developed NIPC-3 neighborhood image parallel computer, providing parallel access to very large neighborhood image. The largest size of neighborhood core is 25 × 24 and the peak speed of neighborhood computing reaches 135 billion multiplication-accumulation operations per second. Experimental results show that NIPC-3 enables much faster implementation for low level processing and can be utilized by more complex algorithms.

关键词： Parallel processing Image processing Image storage Concurrent computing Convolution Data structures Computer architecture Gabor filters Field programmable gate arrays Laboratories

来源：评论

学校读者我要写书评

暂无评论

Piecewise linear aging function for facial age estimation

Piecewise linear aging function for facial age estimation

引用

IEEE International Conference on Image Processing

作者： Shenglan Ben Jiansheng Chen Guangda Su State Key Laboratory of Intelligent Technology and Systems Department of Electronic Engineering Tsinghua University Beijing China

Instead of constructing a complex aging model on the whole age space, a piecewise linear aging function is proposed to approximate the ground truth aging function locally. To handle the `regression toward the mean' problem of local aging function regression, a weighting strategy is used to assign larger weights to the samples near typical aging appearance of each age. In age estimation step, a global aging function is used to predict the test sample's rough age range and the local linear aging function on that range is then used to give a final result. Experimental results show that our method can get more accuracy results in facial age estimation.

关键词： Piecewise linear techniques Aging Piecewise linear approximation Least squares approximation Humans Space technology Testing Polynomials state estimation Laboratories

来源：评论

学校读者我要写书评

暂无评论

Inverse Q filtering to enhance seismic resolution

Inverse Q filtering to enhance seismic resolution

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Ning Tu Wen-kai Lu State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory of Information Science and Technology Department of Automation Tsinghua University China

Due to medium absorption, the resolution of a seismic profile gradually decreases as seismic waves propagate in the earth, known as the attenuation effect. In order to obtain high-resolution seismic profiles which are desirable for characterization of the subsurface formation, we have to quantify the medium absorption effect with medium quality factor Q. After Q is estimated, an inverse Q filter can be designed to enhance the resolution of the seismic profile. Estimation Q from surface seismic data can be difficult since the spectra of the reflected seismic waves are often distorted by thin beds in the formation. In order to remove the influence of thin beds, we apply our HOS based wavelet extraction method here for reliable Q estimation and inverse Q filtering. Synthetic examples verified the effectiveness of the proposed method.

关键词： Filtering Seismic waves Attenuation Absorption Surface waves Data mining Reflectivity Q factor Filters Reflection

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：