检索结果-内蒙古大学图书馆

2013 IEEE Conference on Information and communication Technologies, ICT 2013

作者： Khare, Manish Nigam, Swati Srivastava, Rajneesh Kumar Khare, Ashish Image Processing and Computer Vision Lab Department of Electronics and Communication University of Allahabad Allahabad India

ISBN: (纸本)9781467357586

Moving object segmentation is an important step toward development of any computer vision systems. In the present work, we have proposed a new method for segmentation of moving objects, which is based on single change detection method applied on Contourlet coefficients of two consecutive frames. We have chosen contourlet transform as it has high directionality and represents salient features of image such as edges, curves and contours in better way as compared with wavelet transform. The proposed method is simple and does not require any other parameter except contourlet coefficients. Results after applying the proposed method for segmentation of moving objects are compared with other state-of-the-art methods in terms of visual as well as quantitative performance measures viz. Average difference, Normalized absolute error and Pixel classification based measure. The proposed method is found to be better than other methods. © 2013 IEEE.

关键词： Contourlet transform

来源：评论

学校读者我要写书评

暂无评论

A maximum a posteriori super resolution algorithm based on multidimensional Lorentzian distribution

引用

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2009年第12期10卷 1705-1713页

作者： Wen CHEN Xiang-zhong FANG Yan CHENG Shanghai Key Lab of Digital Media Processing and Transmissions Institute of Image Communication and Information Processing Shanghai Jiao Tong University Shanghai 200240 China College of Information Technology East China University of Political Science and Law Shanghai 201620 China

This paper presents a threshold-free maximum a posteriori (MAP) super resolution (SR) algorithm to reconstruct high resolution (HR) images with sharp edges. The joint distribution of directional edge images is modeled as a multidimensional Lorentzian (MDL) function and regarded as a new image prior. This model makes full use of gradient information to restrict the solution space and yields an edge-preserving SR algorithm. The Lorentzian parameters in the cost function are replaced with a tunable variable, and graduated nonconvexity (GNC) optimization is used to guarantee that the proposed multidimensional Lorentzian SR (MDLSR) algorithm converges to the global minimum. Simulation results show the effectiveness of the MDLSR algorithm as well as its superiority over conventional SR methods.

关键词： Edge preservation Multidimensional Lorentzian distribution (MDL) Super resolution Threshold

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation on segmentation methods for medical images 11

Performance evaluation on segmentation methods for medical i...

引用

Proceedings of the International Conference on Advances in Computing and Artificial Intelligence

作者： Khare, Manish Srivastava, Rajneesh Kumar Khare, Ashish Image Processing and Computer Vision Lab. Department of Electronics and Communication University of Allahabad India

ISBN: (纸本)9781450306355

This paper presents the performance evaluation of different segmentation algorithms for medical images. Accuracy and clarity are very important issues for medical imaging and same in the case with segmentation. In this paper, we have proposed a level set method without reinitialization with some specific shapes for segmentation and compared our proposed approach for segmentation with three other approaches where the first approach is based on region splitting based region growing category, second is based on region merging based region growing category and third is based on level set. This comparison is based on six different performance parameters namely Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Maximum Difference (MD), Normalized Cross Correlation (NCC), Normalized Absolute Error (NAE) and Structural Content (SC). We have compared the proposed approach with three above mentioned approaches for several images, out of which results for four images are provided in this paper, and we find that the approach is better than the other one. © 2011 ACM.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Gait identification by sparse representation

Gait identification by sparse representation

引用

2011 8th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2011, Jointly with the 2011 7th International Conference on Natural Computation, ICNC'11

作者： Gong, Minyan Xu, Yi Yang, Xiaokang Zhang, Wenjun Institute of Image Communication and Information Processing Shanghai China Shanghai Key Lab of Digital Media Processing and Transmissions Shanghai China

ISBN: (纸本)9781612841816

Gait recognition under variations of clothing and carrying condition is still a challenging task. In this paper, we present a gait identification method via sparse representation. We formulate the recognition problem as finding the coefficients of linear combination of the training samples plus an error term and discuss sparse signal representation theory that offers the solution to this problem. Based on the sparse representation computed by l1-minimization, we define a new distance metric to choose non-polluted area and propose a method for gait identification. Compared with the state-of-the-art methods on a large dataset, the proposed method achieves significant performance improvement in identification rates and it shows robustness to variations. © 2011 IEEE.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Regularized Super Resolution Algorithm for Generalized Gaussian Noise

引用

Journal of Donghua University(English Edition) 2010年第1期27卷 25-35页

作者：陈文方向忠刘立峰蒋伟丁大为乔艳涛 Institute of Image Communication and Information Processing Shanghai Jiaotong University Computer and Information Department Shanghai University of Electric Power Key Lab oratory of Intelligent Computing & Signal Processing Ministry of EducationAnhui University

In this paper,an iterative regularized super resolution (SR) algorithm considering non-Gaussian noise is *** on the assumption of a generalized Gaussian distribution for the contaminating noise,an lp norm is adopted to measure the data fidelity term in the cost *** the meantime,a regularization functional defined in terms of the desired high resolution (HR) image is employed,which allows for the simultaneous determination of its value and the partly reconstructed image at each iteration *** convergence is thoroughly *** results show the effectiveness of the proposed algorithm as well as its superiority to conventional SR methods.

关键词： super resolution generalized p-Gaussian distribution regularization parameter

来源：评论

学校读者我要写书评

暂无评论

Blurred image registration by combined invariant of legendre moment and Harris-Laplace detector

Blurred image registration by combined invariant of legendre...

引用

Pacific Rim Symposium on image and Video Technology

作者： Dai, Xiubin Zhang, Hui Shu, Huazhong Luo, Limin Liu, Tianliang School of Computer Science and Engineering Southeast University Nanjing China Lab. of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9780769542850

Since real imaging systems are imperfect, the acquired images are always distorted by blur, scale and rotation transformation. Then the registration of these degraded images has become an important task in many applications in which the moment invariants are usually efficient tools. However, the existing methods can only deal with the slightly distorted images and have the problems of information redundancy. Besides, some methods have overlapping constraint that the images to be aligned should be fully included into the reference images. In this paper, we proposed a novel method in which a new set of combined invariants based on Legendre moment holding for blur, rotation and scale degradation simultaneously were constructed as feature descriptors, and scale-invariant Harris-Laplace detector was applied to exact feature points. The experimental results show that our method can work well without overlapping constraint, especially when the distortion is great. © 2010 IEEE.

关键词： Laplace transforms

来源：评论

学校读者我要写书评

暂无评论

A camera self-calibration method based on dual constraints of multi-view images

A camera self-calibration method based on dual constraints o...

引用

2011 International Conference on Wireless communications and Signal processing, WCSP 2011

作者： Liu, Feng Han, Weiwei Xu, Qiong Lin, Qiongjie Fan, Jingjing Image Processing and Image Communication Jiangsu Key Laboratory Nanjing China Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781457710100

Camera calibration is the essential step of obtaining 3D information from 2D views in the field of computer vision, which is widely used in the area of 3D reconstruction, navigation, visual supervision, etc. A camera self-calibration method based on dual constraints of multi-view images is proposed to make calibration possible when there is no reference calibration block or the movement of camera is arbitrary. In this method, multi-view images are preprocessed first to select three images which are most suitable for camera self-calibration, then we use the method based on the genetic algorithm, the camera parameters are finally estimated by using epipolar geometry matching error and reprojection error as fitness functions as two steps. Experimental results show that the proposed camera self-calibration method is correct and effective. © 2011 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Structured Computational Modeling of Human Visual System for No-reference image Quality Assessment

引用

International Journal of Automation and computing 2021年第2期18卷 204-218页

作者： Wen-Han Zhu Wei Sun Xiong-Kuo Min Guang-Tao Zhai Xiao-Kang Yang MoE Key Lab of Artificial Intelligence AI InstituteShanghai Jiao Tong UniversityShanghai 200240China Institute of Image Communication and Information Processing Shanghai Jiao Tong UniversityShanghai 200240China

Objective image quality assessment(IQA)plays an important role in various visual communication systems,which can automatically and efficiently predict the perceived quality of *** human eye is the ultimate evaluator for visual experience,thus the modeling of human visual system(HVS)is a core issue for objective IQA and visual experience *** traditional model based on black box fitting has low interpretability and it is difficult to guide the experience optimization effectively,while the model based on physiological simulation is hard to integrate into practical visual communication services due to its high computational *** bridging the gap between signal distortion and visual experience,in this paper,we propose a novel perceptual no-reference(NR)IQA algorithm based on structural computational modeling of *** to the mechanism of the human brain,we divide the visual signal processing into a low-level visual layer,a middle-level visual layer and a high-level visual layer,which conduct pixel information processing,primitive information processing and global image information processing,*** natural scene statistics(NSS)based features,deep features and free-energy based features are extracted from these three *** support vector regression(SVR)is employed to aggregate features to the final quality *** experimental comparisons on three widely used benchmark IQA databases(LIVE,CSIQ and TID2013)demonstrate that our proposed metric is highly competitive with or outperforms the state-of-the-art NR IQA measures.

关键词： image quality assessment(IQA) no-reference(NR) structural computational modeling human visual system visual feature extraction

来源：评论

学校读者我要写书评

暂无评论

image retrieval based on character-matching technology

Image retrieval based on character-matching technology

引用

5th International Conference on Information Assurance and Security, IAS 2009

作者： Shan, Zhao Jing, Liu School of Computer Science and Technology Henan Polytechnic University Jiaozuo 454003 China Jiangsu Province Key Lab. on Image Processing and Image Communication Nanjing University of Posts and Communication Nanjing 210003 China

ISBN: (纸本)9780769537443

In order to introduce effective text-retrieval technologies into content-based image retrieval, a novel method based on string-matching technology was presented incorporating the different sensitivity along variant directions of human visual system. The image is firstly divided into non-overlapped blocks and sub-feature is extracted according to the human visual feature. Then, a novel descriptor is defined. Based on which, the sub-features is mapping into characters and the image into the text. Finally, the technology of the character string matching is adopted as the similarity measurement. Meantime, the situation information of character is considered, an adjusted method is proposed. Experimental results show that the proposed method has sound and robust retrieval performance. © 2009 IEEE.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Entropy: A New Parameter for image Deciphering

Entropy: A New Parameter for Image Deciphering

引用

International Conference on Recent Trends in Machine Learning, IOT, Smart Cities and Applications, ICMISC 2020

作者： Cheggoju, Naveen Nawandar, Neha K. Satpute, Vishal R. Image Processing and Computer Vision Lab Department of Electronics and Communication Engineering Visvesvaraya National Institute of Technology Nagpur India

ISBN: (纸本)9789811572333

Data and information, these two terms may look quite similar and also sometimes used with the same meaning. But in-depth, these terms are completely different from each other. This paper mainly focuses on this difference to extract the encrypted information from the data (importantly image data). Here, every aspect of the study and the way of formulation are explained using "Einstein’s theory of relativity" and "Arrow of time" for better understanding. Einstein’s theory is used to explain "how similar things can be seen in different ways?" (here data and information) and arrow of time is used to explain "how the correct information can be extracted from the data?". To explain this concept, an image encrypted using a chaotic logistic map is used. The edge information present in this data is taken as the parameter to differentiate the unorganized data and organized data (correct information). Here, a new parameter called "Randomness parameter (Rp)" is introduced, which gives the entropy (randomness) of the data. The outcome of this parameter is used to differentiate the data and correct information. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Entropy

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：