检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo

作者： Fang Guo Jianbing Shen Xuelong Li Beijing Key Lab of Intelligent Information Technology School of Computer Science Beijing Institute of Technology Center for OPTical IMagery Analysis and Learning (OPTIMAL) State Key Laboratory of Transient Optics and Photonics Xi'an Institute of Optics and Precision Mechanics Chinese Academy of Sciences

ISBN: (纸本)9781479947607

This paper develops a novel learning-based method for detecting stereo saliency in stereopair images. The disparity maps computed from stereopair images provide an additional depth cue for stereo saliency detection. To the best of our knowledge, our approach is the first one to simultaneously detect the stereo saliency of both left and right images using support vector machine (SVM). In our work, the disparity maps are used in two aspects. One is to improve the performance of saliency detection for monocular image. The other one is to maintain the consistency between the stereo matching and saliency maps. In order to meet the above requirements, we propose a new combinational saliency feature to train the stereo images with the labeled saliency ground truth, using support vector machine as the classifier. In the test stage, our approach generates the stereo saliency results according to the trained SVM model. Furthermore, a stereopair saliency dataset containing 400 pairs of images is created to perform the challenging experiments. The experimental results have demonstrated that our method achieves better performance than the state-of-the-art algorithms of single-image saliency detection.

关键词： Stereo saliency detection Stereopair images Support vector machine Feature detection

来源：评论

学校读者我要写书评

暂无评论

A NEW SPARSE FEATURE-BASED PATCH FOR DENSE CORRESPONDENCE

A NEW SPARSE FEATURE-BASED PATCH FOR DENSE CORRESPONDENCE

引用

IEEE International Conference on Multimedia and Expo

作者： Xiameng Qing Jianbing Shen Xuelong Li Yunde Jia Beijing Key Lab of Intelligent Information Technology School of Computer Science Beijing Institute of Technology Center for OPTical IMagery Analysis and Learning (OPTIMAL) State Key Laboratory of Transient Optics and Photonics Xi'an Institute of Optics and Precision Mechanics Chinese Academy of Sciences

ISBN: (纸本)9781479947607

This paper presents a new method to compute the dense correspondences between two images by using the sparse feature-based patches in an energy optimization framework. Many transformation and deformation cues such as color, scale and rotation should be considered when we finding dense correspondences between images. However, most existing methods only consider part of these transformations, which will introduce the uncorrect correspondence results. In terms of the property of the sparse feature and the principle that nearest sub-scenes and neighbors are much more similar, we design a new energy optimization to guide the dense matching process. Both transformation and deformation are considered in our energy optimization framework since we design the feature-based patches. Thus, our algorithm can match the complicated scenes and objects robustly. At last, a local refinement technique is proposed to solve the perturbation of the matched patches. Experimental results demonstrate that our method outperforms the state-of-the-art algorithms.

关键词： Dense Correspondence Optimization Patch Match

来源：评论

学校读者我要写书评

暂无评论

Joint optimization toward effective and efficient image search

引用

IEEE Transactions on Cybernetics 2013年第6期43卷 2216-2227页

作者： Wei, Shikui Xu, Dong Li, Xuelong Zhao, Yao Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing 100044 China School of Computer Engineering Nanyang Technological University 639798 Singapore Singapore Center for OPTical IMagery Analysis and Learning State Key Laboratory of Transient Optics and Photonics Xi'An Institute of Optics and Precision Mechanics Xi'an 710119 China Institute of Information Science Beijing Jiaotong University Beijing 100044 China State Key Laboratory of Rail Traffic Control and Safety Beijing 100044 China

The bag-of-words (BoW) model has been known as an effective method for large-scale image search and indexing. Recent work shows that the performance of the model can be further improved by using the embedding method. While different variants of the BoW model and embedding method have been developed, less effort has been made to discover their underlying working mechanism. In this paper, we systematically investigate the image search performance variation with respect to a few factors of the BoW model, and study how to employ the embedding method to further improve the image search performance. Subsequently, we summarize several observations based on the experiments on descriptor matching. To validate these observations in a real image search, we propose an effective and efficient image search scheme, in which the BoW model and embedding method are jointly optimized in terms of effectiveness and efficiency by following these observations. Our comprehensive experiments demonstrate that it is beneficial to employ these observations to develop an image search algorithm, and the proposed image search scheme outperforms state-of-the-art methods in both effectiveness and efficiency. © 2013 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

An adaptive and effective single image dehazing algorithm based on dark channel prior

An adaptive and effective single image dehazing algorithm ba...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Qingsong Zhu Shuai Yang Pheng Ann Heng Xuelong Li Shenzhen Institutes of Advanced Technology Chinese Advanced of Sciences Shenzhen China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong School of Electronic Engineering Tsinghua University Beijing Centre for OPTical IMagery Analysis and Learning (OPTIMAL) Chinese Academy of Sciences Xi'an Shanxi P.R. China

ISBN: (纸本)9781479927456

In this paper, we describe a novel and effective single image enhancement algorithm for haze image. As we observe that, the contrast and intensity of haze image after using dark channel prior approach will unavoidably tend to be lower than those of the real scene, we proposed a method using histogram specification to make an improvement on image after dark channel prior approach. We make a large number of experiment and find that, if dealing with a haze image with large background area and low contrast, dark channel prior result will become dark, also a general haze image after dark channel occurs different degree of anamorphose. We introduce an adaptive algorithm to repair the different kinds of anamorphose on the hazy image after dark channel prior. The experimental results shows that our method make the dehazing result more close to real scene.

关键词： Histograms Image color analysis Noise Cameras computer vision Adaptive equalizers

来源：评论

学校读者我要写书评

暂无评论

A-Optimal Non-negative Projection for image representation

A-Optimal Non-negative Projection for image representation

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Haifeng Liu Zheng Yang Zhaohui Wu Xuelong Li College of Computer Science University of Zhejiang Hangzhou Zhejiang China Center for OPTical IMagery Analysis and Learning (OPTIMAL) State Key Laboratory of Transient Optics and Photonics Xian Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi'an Shaanxi China

As a central problem in computer vision and pattern recognition, data representation has attracted great attention in the past years. Non-negative matrix factorization (NMF) which is a useful data representation method makes great contribution on finding the latent structure of the data and leads to a parts-based representation by decomposing the data matrix into a few bases and encodings with nonnegative constraints. However, non-negative constraint is insufficient for getting more robust data representation. In this paper, we propose a novel method, called A-Optimal Non-negative Projection (ANP) for image data representation and further analysis. ANP imposes a constraint on the encoding factor as a regularizer during matrix factorization. In this way, the learned data representation leads to a stable linear model no matter what kind of data label is selected for further processing. Thus, it can preserve more intrinsic characteristics of the data regardless of any specific labels. We demonstrate the effectiveness of this novel algorithm through a set of evaluations on real world applications.

关键词： Matrix decomposition Optimization Vectors Encoding Principal component analysis Covariance matrix Databases

来源：评论

学校读者我要写书评

暂无评论

Intrinsic Images Using Optimization

Intrinsic Images Using Optimization

引用

IEEE Conference on computer Vision and Pattern Recognition

作者： Jianbing Shen Xiaoshan Yang Yunde Jia Xuelong Li Beijing Laboratory of Intelligent Information Technology School of Computer Science Beijing Institute of Technology Center for OPTical IMagery Analysis and Learning (OPTIMAL) State Key Laboratory of Transient Optics and Photonics Xi'an Institute of Optics and Precision Mechanics Chinese Academy of Sciences

ISBN: (纸本)9781457703942

In this paper, we present a novel intrinsic image recovery approach using optimization. Our approach is based on the assumption of color characteristics in a local window in natural images. Our method adopts a premise that neighboring pixels in a local window of a single image having similar intensity values should have similar reflectance values. Thus the intrinsic image decomposition is formulated by optimizing an energy function with adding a weighting constraint to the local image properties. In order to improve the intrinsic image extraction results, we specify local constrain cues by integrating the user strokes in our energy formulation, including constant-reflectance, constant-illumination and fixed-illumination brushes. Our experimental results demonstrate that our approach achieves a better recovery of intrinsic reflectance and illumination components than by previous approaches.

关键词： intrinsic image illumination Lighting PREMISES images Image decomposition

来源：评论

学校读者我要写书评

暂无评论

Utilizing homotopy for single image superresolution

Utilizing homotopy for single image superresolution

引用

Asian Conference on Pattern Recognition (ACPR)

作者： Xiaoqiang Lu Pingkun Yan Yuan Yuan Xuelong Li Haoliang Yuan Center for OPTical IMagery Analysis and Learning (OPTIMAL) State Key Laboratory of Transient Optics and Photonics Xian Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi'an Shaanxi China Faculty of Mathematics and Computer Science Hubei University Wuhan Hubei China

ISBN: (纸本)9781457701221

learning an appropriate dictionary is a critical issue for sparse representation based super-resolution algorithms. A good dictionary can well represent an underlying image. In super-resolution algorithms, classical dictionary learning doesn't consider the information of test image which contains the information of the reconstructed image. In this paper, the new dictionary is design for image super-resolution, incorporating both training image patches and test image patches for training. It is important for dictionary learning to adaptively choose the training image patches and test image patches which effectively represent the reconstructed image structures. In the new learning strategy, a homotopy method is applied to choose the parameter that yields a proper balance between the use of training image patches and test image patches. The homotopy method is used to track the homotopy path leading to the solution to the desired problem at the terminal point. Compared with other state-of-the-art learning methods, our algorithm learns an over-complete dictionary by exploiting the information of the given test image and training images. The experimental results show that the proposed method is able to achieve better experimental results in terms of both PSNR and visual perception.

关键词： Dictionaries Image resolution Strontium Training Image reconstruction Equations Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Image denoising via weight regression

Image denoising via weight regression

引用

Asian Conference on Pattern Recognition (ACPR)

作者： Yi Tang Yuan Yuan Pingkun Yan Xuelong Li Hui Zhou Luoqing Li Center for OPTical IMagery Analysis and Learning (OPTIMAL) State Key Laboratory of Transient Optics and Photonics Xian Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi'an Shaanxi China Faculty of Mathematics and Computer Science Hubei University Wuhan Hubei China

ISBN: (纸本)9781457701221

The core of image denoising is making a trade-off between removing noise and preserving details of noised image. To remove noise, the denoising algorithm based on K-SVD is employed in this paper. Though the power of such denoising algorithm has been verified by a mount of experiments, many meaningful details of noised image cannot be well maintained. To preserve details of noised image, therefore, local structure information of noised image which is described by the steering kernel is considered in image denoising. In fact, a weighted regression method where the weights are defined by the steering kernel is used to recover the meaningful details of noised image. Experimental results have shown that more meaningful details of noised image are preserved by the proposed algorithm.

关键词： Kernel Dictionaries Noise Noise reduction Image denoising Signal processing algorithms Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Local adaptive dictionary based image denoising

Local adaptive dictionary based image denoising

引用

Asian Conference on Pattern Recognition (ACPR)

ISBN: (纸本)9781457701221

In this paper, the problem of balancing the noise removing and the image details preserving is considered. To remove noise adaptively, local dictionaries and sparse coding techniques are used. For a noised image patch, the local dictionary corresponding to it and the sparse coding technique are used to generate the sparse coding vector of the given patch. Then the noise of the given patch can be removed without any information on noise level by setting all components be zero but preserving largest component of the sparse coding vector. Because too much information on image details are removed with noise by the above process, a local weighted regression is adopted to refine the denoising image with the help of the information on the local geometry structure of noised image. Various experiments have been accomplished and prove our method to be effective in balancing the noise removing and the image details preserving.

关键词： Dictionaries Noise reduction Noise Clustering algorithms Vectors Image denoising Kernel

来源：评论

学校读者我要写书评

暂无评论

Single-image super-resolution based on semi-supervised learning

Single-image super-resolution based on semi-supervised learn...

引用

Asian Conference on Pattern Recognition (ACPR)

作者： Yi Tang Yuan Yuan Pingkun Yan Xuelong Li Xiaoli Pan Luoqing Li Center for OPTical IMagery Analysis and Learning (OPTIMAL) State Key Laboratory of Transient Optics and Photonics Xian Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi'an Shaanxi China Faculty of Mathematics and Computer Science Hubei University Wuhan Hubei China

Supervised learning-based methods are popular in single-image super-resolution (SR), and the underlying idea is to learn a map from input low-resolution (LR) images to target high-resolution (HR) images based on a training set. The generalization of the learned map ensures the well performance of these methods on various test images. However, the universality of these methods weakens their specificity. To enhance the performance of learning-based methods on given test images, a semi-supervised learning-based method is firstly proposed for single-image SR. In particular, test image patches are used to learn a dictionary for defining a test-data-dependent feature space. By using the learned dictionary, all LR training samples can be mapped into the test-data-dependent feature space, which makes the information contained in the training set be understood according to the given SR task. Finally, a regression function defined on the test-data-dependent feature space is learned from the refined training samples for generating SR images. The experimental results show that more details are recovered by the proposed semi-supervised method than its supervised version, which means it is a key to balance the universality and the specificity of a regression function in learning-based SR.

关键词： Training Strontium Image resolution Dictionaries Signal resolution PSNR Interpolation

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：