检索结果-内蒙古大学图书馆

Chinese Conference on Pattern Recognition

作者： Zuo, Xin Dai, Xiubin Luo, Limin Zhu, Feng Zhang, Feng Lab. of Image Science and Technology School of Computer Science and Engineering Southeast University Nanjing 210096 China School of Computer Science and Engineering Jiangsu University of Science and Technology Zhenjiang 212003 China

ISBN: (纸本)9781424472109

In this paper, we propose a more accurate method to align two images under rotation, scaling, blurring in weak texture image. This method utilizes the uniform log-polar sampling (ULP) technique in order to overcome the problem of over-sampling in the fovea area and under-sampling in the peripheral area which affects the accuracy of registration. The proposed method can effectively estimate the rotation and scale parameters more precisely and can also deal with center occlusion. Experimental results demonstrate the effectiveness and robustness of the proposed approach in registrations with geometry transformation, blurring and center occlusion. ©2010 IEEE.

关键词： image registration

来源：评论

学校读者我要写书评

暂无评论

Semantic analysis of 3D anatomical medical images for sub-image retrieval

Semantic analysis of 3D anatomical medical images for sub-im...

引用

2nd MICCAI International Workshop on Medical Content-Based Retrieval for Clinical Decision Support, MCBR-CDS 2011

作者： Venkatraghavan, Vikram Ranjan, Sohan Medical Imaging and PACS Lab. School of Medical Science and Technology Indian Institute of Technology Kharagpur India Medical Image Analysis Lab. John F. Welch Technology Center GE Global Research India

ISBN: (纸本)9783642284595

Voluminous medical images are critical assets for clinical decision support systems. Retrieval based on the image content can help the clinician in mining images relevant to the current case from a large database. In this paper we address the problem of retrieving relevant sub-images with similar anatomical structures as that of the query image across modalities. The images in the database are automatically annotated with information regarding body region depicted in the scan and organs present, along with their localizing bounding box. For this purpose, initially a coarse localization of body regions is done in the 2D space taking contextual information into account. Following this, finer localization and verification of organs is done using a novel, computationally efficient fuzzy approximation method for constructing 3D texture signatures of organs of interest. They are then indexed using an inverted-file data structure which helps in ranked retrieval of relevant images. Apart from retrieving sub-images across modalities by image example, automatic annotation and efficient indexing allows query by text, limited only by the semantic vocabulary. The algorithm was tested on a database of non-contrast CT and T1-weighted MR volumes. Quantitative assessment of the proposed algorithm was evaluated using ground-truth database sanitized by medical experts. © 2012 Springer-Verlag.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Electronic trace fossil image retrieval based on extended direction local binary pattern

引用

2012 International Conference on Mechanical and Electronic Engineering, ICMEE 2012

作者： Wu, Xiaosheng Sun, Junding School of Computer Science and Technology Henan Polytechnic University Jiaozuo 454003 China Image Processing and Image Communication Lab. Nanjing University of Post and Telecommunication Nanjing 210003 China

ISBN: (纸本)9783642315275

Based on the direction local binary pattern (dLBP) and the center-symmetric local binary pattern (CS-LBP), an improved direction local binary pattern (idLBP) was presented. The directionality, coarseness and contrast of a texture region were considered together in the new definition. LBP, dLBP and idLBP were firstly tested on two commonly used texture image sets. Finally, idLBP was used for electronic trace fossil image retrieval. The results show that idLBP gives the best retrieval performance in the three descriptors. © 2013 Springer-Verlag.

关键词： image retrieval

来源：评论

学校读者我要写书评

暂无评论

Improved region local binary patterns for image retrieval

Improved region local binary patterns for image retrieval

引用

Computer science and Information Engineering, CSIE 2012

ISBN: (纸本)9783642301254

Two extended patterns, direction local binary pattern (D-LBP) and variance direction local binary pattern (vD-LBP) were introduced in the paper. More texture features are obtained in the new operators by introducing a variant threshold. The descriptors mentioned in the paper were firstly tested and evaluated on CUReT texture image database. Experimental results show that the two extended operators give better performance than D-LBP and vD-LBP respectively. Finally, the operators were used for trace fossils image retrieval and the results denote that the proposed operator, tvD-LBP is the most effective method for trace fossils image description in the four descriptors. © 2012 Springer-Verlag GmbH.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Contribution of non-scrambled chroma information in privacy-protected face images to privacy leakage

Contribution of non-scrambled chroma information in privacy-...

引用

10th International Workshop on Digital-Forensics and Watermarking, IWDW 2011

作者： Sohn, Hosik Lee, Dohyoung De Neve, Wesley Plataniotis, Konstantinos N. Ro, Yong Man Image and Video Systems Lab. Department of Electrical Engineering Korea Advanced Institute of Science and Technology Korea Republic of Multimedia Lab. Department of Electrical and Computer Engineering University of Toronto Canada

ISBN: (纸本)9783642322044

To mitigate privacy concerns, scrambling can be used to conceal face regions present in surveillance video content. Given that lightweight scrambling tools may not protect chroma information in order to limit bit rate overhead in heterogeneous usage environments, this paper investigates how the presence of non-scrambled chroma information in face regions influences the effectiveness of automatic and human face recognition (FR). To that end, we apply three automatic FR techniques to face images that have been privacy-protected by means of a layered scrambling technique developed for Motion JPEG XR, testing the effectiveness of automatic FR and layered scrambling using various experimental conditions. In addition, we investigate whether agreement exists between the judgments of 32 human observers and the output of automatic FR. Our experimental results demonstrate that human observers are not able to successfully recognize face images when simultaneously visualizing scrambled luma and non-scrambled chroma information. However, when an adversary has access to the coded bit stream structure, the presence of non-scrambled chroma information may significantly contribute to privacy leakage. By additionally applying layered scrambling to chroma information, our experimental results show that the amount of privacy leakage can be substantially decreased at the cost of an increase in bit rate overhead, and with the increase in bit rate overhead dependent on the number of scalab.lity layers used. © 2012 Springer-Verlag.

关键词： Scalab.lity

来源：评论

学校读者我要写书评

暂无评论

Architecture of behavior-based and robotics self-optimizing memory controller

Architecture of behavior-based and robotics self-optimizing ...

引用

2009 IEEE International Conference on Robotics and Automation, ICRA '09

作者： Osman, Hassab Elgawi Image Science and Engineering Lab. Tokyo Institute of Technology School of Engineering 4259 Nagatsuta Midori-ku Yokohama 226-8503 Japan

ISBN: (纸本)9781424427895

In this paper we represent a preliminary research on designing a behavior-based adaptive system utilizing self-optimizing memory controller. Rather than holistic search for the whole memory contents the model adopt associated feature analysis to successively memorize a newly experience state-action pair as an action of past experience, produce motor commands that make the controlled system to behave desirably in the future. Actor-Critic learning is used to adaptively tuning the control parameters, while an on-line variant of random forests (RF) learner is used to approximate the policy of Actor and the value function of Critic. Learning capability of the proposed model is experimentally examined through a task of Cart-Pole balancing problem, designed in mind as computation with perception. The result shows that the robot with self-optimizing memory acquired behaviors such as balancing the pole, displays planning based on past experiences. © 2009 IEEE.

关键词： Poles

来源：评论

学校读者我要写书评

暂无评论

A new fuzzy ART neural network based on dual competition and resonance technique

A new fuzzy ART neural network based on dual competition and...

引用

3rd International Symposium on Neural Networks, ISNN 2006 - Advances in Neural Networks

作者： Zhang, Lei Wang, Guoyou Wang, Wentao Lab. for Biometric and Medical Image Processing Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)354034439X

A new Fuzzy ART neural network model based on dual competition and resonance technique is proposed. This new model takes the competition and resonance method of the input nodes into the output nodes, putting the input nodes and output nodes competition and resonance together, solves the over-segmentation of the FART algorithm due to the vigilance's increase in the application of the image segmentation. Experimental results have shown that compared with the original FART, this algorithm has a better segmentation and antinoise performance. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

SAR image despeckling based on edge detection and nonsubsampled second generation bandelets

引用

Journal of Systems Engineering and Electronics 2009年第3期20卷 519-526页

作者： Zhang Wenge~(1,2),Liu Fang~(1,2),Jiao Licheng~(2,3)& Gao Xinbo~(2,3) 1.School of Computer science and technology,Xidian Univ.,Xi’an 710071,P.R.China 2.Key lab.of Intelligent Perception and image Understanding of Ministry of Education of China,Xi’an 710071,P.R.China 3.Inst,of Intelligent Information Processing,Xidian Univ.,Xi’an 710071,P.R.China School of Computer Science and Technology Xidian Univ. Xi'an 710071 P. R. China Key Lab. of Intelligent Perception and Image Understanding of Ministry of Education of China Xi'an 710071 P. R. China Key Lab. of Intelligent Perception and Image Understanding of Ministry of Education of China Xi'an 710071 P. R. China Inst. of Intelligent Information Processing Xidian Univ. Xi'an 710071 P. R. China

To preserve the sharp features and details of the synthetic aperture radar （SAR） image effectively when despeckling, a despeckling algorithm with edge detection in nonsubsampled second generation bandelet transform （NSBT） domain is proposed. First, the Canny operator is utilized to detect and remove edges from the SAR image. Then the NSBT which has an optimal approximation to the edges of images and a hard thresholding rule are used to approximate the details while despeckling the edge-removed image. Finally, the removed edges are added to the reconstructed image. As the edges axe detected and protected, and the NSBT is used, the proposed algorithm reaches the state-of-the-art effect which realizes both despeckling and preserving edges and details simultaneously. Experimental results show that both the subjective visual effect and the mainly objective performance indexes of the proposed algorithm outperform that of both Bayesian wavelet shrinkage with edge detection and Bayesian least square-Gaussian scale mixture （BLS-GSM）.

关键词： computer image processing synthetic aperture radar speckle edge detection nonsubsampled second generation bandelet transform Canny operator threshold shrinkage.

来源：评论

学校读者我要写书评

暂无评论

Real-time face detection using multiple instances boosting cascade

Real-time face detection using multiple instances boosting c...

引用

2009 Chinese Conference on Pattern Recognition, CCPR 2009 and the 1st CJK Joint Workshop on Pattern Recognition, CJKPR

作者： Duanduan, Liu Hua, Zhang Lin, Luo Limin, Luo Lab. of Image Science and Technology Southeast University Nanjing 210096 China College of Software Engineering Southeast University Nanjing 210096 China

ISBN: (纸本)9781424441990

Considering the conventional defects of boosting cascade, such as overwhelmed training computation, inaccurate threshold adjustment, face detection based on multiple instances and boosting cascade presents a new way. This paper explores the solutions of boosting machine learning and its threshold adjustment strategies, which utilize separated training sets, large scale set with bootstrapping, various parameters adjustment, and multiple instance threshold adjustment. After applying these strategies, our method greatly improve the speed and accuracy of face detection, and explicitly upgrade the inside methodology of conventional boosting cascade face detection. ©2009 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

image analysis by discrete orthogonal moments

引用

Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University 2006年第5期40卷 796-800+804页

作者： Liang, Jun Shu, Hua-Zhong Zhu, Hong-Qing Luo, Li-Min Lab. of Image Science and Technology Southeast Univ. Nanjing 210096 China

A new discrete orthogonal moment-Hahn moment based on the discrete classical Hahn polynomials was introduced. The recurrence relations of the Hahn polynomials were derived. These relations, combining with the symmetry property, are used to evaluate the Hahn polynomial values. The strategy can reduce the accumulation of numerical errors in the computation of high order polynomial values so that the original image can be accurately reconstructed. The image reconstruction ability using Hahn moment was compared with that using Tchebichef moment. The experimental results demonstrate the effectiveness of the proposed method.

关键词： image analysis

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：