检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Li, Yuanzhuo Zheng, Yunan Chen, Jie Xu, Zhenyu Liu, Yiguang Vision and Image Processing Lab School of Computer Science Sichuan University China

Among the major remaining challenges for single image super resolution (SISR) is the capacity to recover coherent images with global shapes and local details conforming to human vision system. Recent generative adversarial network (GAN) based SISR methods have yielded overall realistic SR images, however, there are always unpleasant textures accompanied with structural distortions in local regions. To target these issues, we introduce the gradient branch into the generator to preserve structural information by restoring high-resolution gradient maps in SR process. In addition, we utilize a U-net based discriminator to consider both the whole image and the detailed per-pixel authenticity, which could encourage the generator to maintain overall coherence of the reconstructed images. Moreover, we have studied objective functions and LPIPS perceptual loss is added to generate more realistic and natural details. Experimental results show that our proposed method outperforms state-of-the-art perceptual-driven SR methods in perception index (PI), and obtains more geometrically consistent and visually pleasing textures in natural image restoration. © 2021, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

BIORTHOGONAL WAVELET TRANSFORM BASED image FUSION USING ABSOLUTE MAXIMUM FUSION RULE

BIORTHOGONAL WAVELET TRANSFORM BASED IMAGE FUSION USING ABSO...

引用

IEEE Conference on Information & Communication Technologies

作者： Om Prakash Richa Srivastava Ashish Khare Image Processing and Computer Vision Lab Department of Electronics and Communication University of Allahabad

ISBN: (纸本)9781467357593

The objective of image fusion is to combine relevant information from two or more images of the same scene into a single composite image which is more informative and is more suitable for human and machine perception. In recent past, different methods of image fusion have been proposed in literature both in spatial domain and wavelet domain. Spatial domain based methods produce spatial distortions in the fused image. Spatial domain distortion can be well handled by the use of wavelet transform based image fusion methods. In this paper, we propose a pixel-level image fusion scheme using multiresolution Biorthogonal wavelet transform (BWT). Wavelet coefficients at different decomposion levels are fused using absolute maximum fusion rule. Two important properties wavelet symmetry and linear phase of BWT have been exploited for image fusion because they are capable to preserve edge information and hence reducing the distortions in the fused image. The performance of the proposed method have been extensively tested on several pairs of multifocus and multimodal images both free from any noise and in presence of additive white Gaussian noise and compared visually and quantitatively against existing spatial domain methods. Experimental results show that the proposed method improves fusion quality by reducing loss of significant information available in individual images. Fusion factor, entropy and standard deviation are used as quantitative quality measures of the fused image.

关键词： image fusion Multifocus images Multimodality Biorthogonal wavelet transform Fusion rules

来源：评论

学校读者我要写书评

暂无评论

LICENSE PLATE LOCALIZATION BASED ON EDGE-GEOMETRICAL FEATURES USING MORPHOLOGICAL APPROACH

LICENSE PLATE LOCALIZATION BASED ON EDGE-GEOMETRICAL FEATURE...

引用

IEEE International Conference on image processing

作者： Jinn-Li Tan Syed A.R Abu-Bakar Musa M. Mokji Computer Vision Video and Image Processing Lab ECE Department Universiti Teknologi Malaysia

ISBN: (纸本)9781479923427

Malaysian car plates in general appear in different character styles, types (either single or double row), sizes, spacing and character counts. Such variations cause even detecting and localizing these plates a difficult problem. The problem of localization is aggravated further during night time due to poor illumination. In this paper, we introduce the idea of edgegeometrical features in detecting these plates. The edge part is obtained from the use of Difference of Gaussian operation followed by Sobel vertical edge mask. Prior to that, gamma correction is applied to increase the detection of edges. We then apply morphological operations to get the plate region candidates. Using these regions, together with the edge image, we calculate geometrical features of these regions and use rule-based classifier to correctly identify the true plate region. Finally, we test out method using our own data set which contained 250 images captured during day time and 100 images captured during night time. The result of the proposed method shows 96.9% success rate.

关键词： Gamma correction Difference of Gaussian Sobel vertical mask Rule-based classifier Bone Plate PLATES edge image plate Licence Plates Edge detection Morphological operations double-row

来源：评论

学校读者我要写书评

暂无评论

labelling color images by modelling the colors density using a linear combination of Gaussians and EM algorithm

Labelling color images by modelling the colors density using...

引用

IEEE International Conference on image processing

作者： Asem M. Ali Amal A. Farag Aly A. Farag Computer Vision and Image Processing Laboratory (CVIP Lab) University of Louisville Louisville KY

Parametric density estimation is widely used to solve many image processing problems. We examined the parametric estimation using linear combination of 1D Gaussians in many works. In this work, we extend our model to estimate density of the colors in color images. We approximate the marginal density of each class in the empirical probability density function by a 3D Gaussian distribution. Then, the deviation between the estimated and the empirical densities is modelled using a linear combination of 3D Gaussians with positive and negative components. We estimate the parameters of this model using our modified EM algorithm. The proposed framework demonstrates very promising experimental results of color images labelling and can be integrated with many other frameworks.

关键词： labeling Color Gaussian processes Function approximation Probability density function image processing Gaussian distribution Parameter estimation image segmentation Gaussian approximation

来源：评论

学校读者我要写书评

暂无评论

Robust virtual forces-based camera positioning using a fusion of image content and intrinsic parameters

Robust virtual forces-based camera positioning using a fusio...

引用

International Conference on Information Fusion

作者： A.E. Abdel-Hakim A.A. Farag Computer Vision and Image Processing Laboratory CVIP Lab University of Louisville Louisville KY USA

In this paper, we present a novel and robust model for camera planning in smart vision systems. The proposed approach uses virtual forces to adjust camera parameters (pan and tilt) to the most proper values with respect to the application. The proposed model employs the information in the acquired image and some of the intrinsic camera parameters to estimate pan and tilt displacements required to bring a target object into a specific location of interest in the image. Our model is a general framework and any vision system can be easily modeled to use it. This approach has several advantages over previous work in camera planning. It is portable, expandable, robust, and flexible. Also, there is no need for complicated calibration for the cameras or their pan-tilt heads. The results show that our approach is efficient even with poor system initialization and it is robust against possible weakness in the auxiliary algorithms used.

关键词： Robustness Cameras Machine vision Calibration Process planning Head Lenses Focusing Surveillance computer vision

来源：评论

学校读者我要写书评

暂无评论

Density estimation using a new AIC-type criterion and the EM algorithm for a linear combination of Gaussians

Density estimation using a new AIC-type criterion and the EM...

引用

IEEE International Conference on image processing

作者： Asem M. Ali Aly A. Farag Computer Vision and Image Processing Laboratory (CVIP Lab) University of Louisville Louisville KY USA

We propose a new approach that approximates an empirical probability density function of scalar data with a linear combination of Gaussians (LCG). The proposed algorithm approximates the marginal density of each class using a Gaussian distribution. Number of the classes and their distributions parameters are estimated using a new Akaike Information Criterion (AlC)-type criterion and the Expectation- Maximization (EM) approach. Each class does not follow perfect Gaussian distribution so we refine the initial LCG model using a modified EM algorithm. The modified EM algorithm approximates the marginal density of each class using a LCG with positive and negative components. Experiments in segmenting multimodal medical images show that the developed technique gives promising accurate results.

关键词： Gaussian processes Function approximation Probability density function Gaussian approximation Gaussian distribution Parameter estimation image processing Clustering algorithms image segmentation Probability distribution

来源：评论

学校读者我要写书评

暂无评论

Shape-constraint for accurate segmentation in remote sensing imagery

Shape-constraint for accurate segmentation in remote sensing...

引用

International Conference on Information Fusion

作者： A. El-Baz R. Mohamed A. Farag Computer Vision and Image Processing Laboratory (CVIP Lab) University of Louisville Louisville KY USA

A new approach is proposed for the segmentation of remote sensing images which is based on using a prior shape information. This information is obtained from a set of signed distance functions (SDF). Each SDF represents the training data set as a histogram of the occurrences of the data points inside and outside a specific object. A statistical approach is proposed for modeling each SDF, which is considered to have a random distribution. The mean field theory-based support vector machines (MF-based SVM) density estimator is used to estimate the probability density function which underlies the random distribution of the SDF. The statistical modeling of shapes enables realistic representation of objects especially those which are not contiguous within the image; i.e., objects which consist of multiple regions. This modeling is used to substitute for the class priors in a Bayes segmentation setup, in which the class conditional probabilities are estimated using the MF-based SVM algorithm also. Experiments with multispectral remote sensing data show that the proposed segmentation approach is more accurate and robust than other known alternatives.

关键词： image segmentation Remote sensing Shape measurement Surface cleaning Support vector machines computer vision Pixel image processing laboratories Training data

来源：评论

学校读者我要写书评

暂无评论

A novel framework for N-D multimodal image segmentation using graph cuts

A novel framework for N-D multimodal image segmentation usin...

引用

IEEE International Conference on image processing

作者： Asem M. Ali Aly A. Farag Computer Vision and Image Processing Laboratory (CVIP Lab) University of Louisville Louisville KY USA

This work proposes a new MAP-based segmentation framework of multimodal images. In this work a joint MGRF model is used to describe the image. The main focus here is a more accurate model identification. For a known number of classes in the given image, the empirical distributions of this image signals are precisely approximated by a LCG distributions with positive and negative components. Gibbs potential, which is used to identify the spatial interaction between the neighboring pixels, is analytically estimated. Finally, an energy function using the previous models is formulated and is globally minimized using graph cuts. Experiments show that the developed technique gives promising accurate results compared to other known algorithms.

关键词： image segmentation Pixel Joining processes labeling image processing Gray-scale Robustness Object segmentation computer vision laboratories

来源：评论

学校读者我要写书评

暂无评论

On averaging face images for recognition under pose variations

On averaging face images for recognition under pose variatio...

引用

International Conference on Pattern Recognition

作者： Xiaozheng Zhang Sanqiang Zhao Yongsheng Gao Computer Vision and Image Processing Lab Institute for Integrated and Intelligent Systems Griffith University Australia

ISBN: (纸本)9781424421749

Recently, psychological studies showed that averaging human face images greatly improves the performance of face recognition under various pose, illumination, expression, and/or aging conditions. This paper investigates quantitatively the mechanism of the face averaging process in face recognition specifically against pose variations. Facilitated with 3D face dataset, the process of face averaging is tested on face images free from human errors and misalignments. Single images are chosen as gallery and the averaged views as probe in all the experiments. Three different scenarios are experimented, i.e., identification using single gallery images, identification using different gallery images, and averaging using unbalanced range of input image. The experimental results show that the averaging process under pose variations is equivalent to generating a face view in an average pose and the improvement in face recognition is subject to the conditions that the gallery pose is close to the average probe pose.

关键词： Face recognition image recognition Probes Lighting Testing Humans Face detection Psychology Aging image databases

来源：评论

学校读者我要写书评

暂无评论

Remote sensing image segmentation using SVM with automatic selection for the kernel parameters

Remote sensing image segmentation using SVM with automatic s...

引用

International Conference on Information Fusion

作者： R. Mohamed A. El-Baz A. Farag Computer Vision and Image Processing Laboratory (CVIP Lab) University of Louisville Louisville KY USA

The kernel function plays a basic role in support vector machines (SVM) algorithms. This paper presents an automatic method for selecting the parameters of the Gaussian radial basis function (GRBF) kernel which is one of the commonly used forms in SVM regression algorithms. The proposed method uses the expectation maximization (EM) algorithm for the automatic selection. The SVM regression algorithm is used to solve two major problems in remote sensing image segmentation: the density estimation problem and the Markov random field modeling problem. The density estimation is used for class conditional probabilities in Bayesian setups. The MRF is used for region modeling in boosting the Bayesian image segmentation. The proposed algorithms are integrated in a framework for remote sensing image segmentation. Experimental evaluation of the proposed algorithms using synthetic data set and hyperspectral data set illustrates the outstanding performance of the proposed algorithms.

关键词： Remote sensing image segmentation Support vector machines Kernel Probability Markov random fields Bayesian methods Covariance matrix computer vision image processing

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：