A weighted H1 seminorm regularization method for Fredholm integral equations of the first kind

Many problems in mathematics and engineering lead to Fredholm integral equations of the first kind, e.g. signal and image processing. These kinds of equations are difficult to solve numerically since they are ill-posed. Therefore, regularization is required to obtain a reasonable approximate solution. This paper presents a new regularization method based on a weighted H¹ seminorm. Details of numerical implementation are given. Numerical examples, including one-dimensional and two-dimensional integral equations, are presented to illustrate the efficiency of the proposed approach. Numerical results show that the proposed regularization method can restore edges as well as details.     

模糊综合评价法在长江下游贵池河段水质评价中的应用

对水质评价存在诸多方法,而模糊综合评价法具有评价结果合理、更接近客观实际等优点,因而得到越来越广泛的应用。通过模糊评价方法对长江下游贵池河段2005～2009年间水环境综合评价,并采用加权平均原则求取隶属等级,取得较好的效果。     

广义逆的计算与最小二乘估计

给出了某些广义逆的计算方法,将这些结果应用于观测系统的参数估计,给出了系统无加权和加权最小二乘的最新估计结果,推广了[1]的工作,同时简化了[2]中求多个相容矩阵方程公共解的算法。     

城镇土地定级信息系统的研制和开发

土地定级过程繁杂,周期长,数据处理量庞大,需要一套符合规程要求,科学、简便、实用的系统来辅助土地管理部门的工作,文中探讨了以计算机作为辅助工具,进行城镇土地定级系统的研制和开发。     

广义Calderón—Zygmund算子交换子的加权有界性

主要讨论由Lipschitz函数b与广义C—Z算子T生成的交换子[b,T]在加权Hardy空间上的有界性,证明了[b,T]是从Lw^p p到Lw^q q有界的和从H^pω^p到L^qω^q上的有界性．     

局部归一化融合EW-Gabor特征的光照变化人脸识别

针对光照变化人脸识别问题,提出了一种基于局部归一化融合熵加权Gabor特征方法。首先,计算类熵加权向量;然后,对图像进行局部归一化,并且计算输入图像的Borda计数,从而消除低值Gabor jet比较矩阵;最后,利用投票得分策略和k近邻分类器完成人脸识别。在扩展YaleB和AR人脸数据库上进行实验评估,在AR上的识别率可接近100%,相比其它几种较新的局部特征方法,本文方法取得了更高的识别精度,并且在一定程度上减少了计算开销。     

一种基于图像分块加权的（2D）2PCA人脸特征提取方法

论文针对二维主成分分析法（2DPCA）表征信息不全面且系数多的不足,提出分块加权处理的双向2DPCA（（2D）2PCA）方法提取人脸特征。该方法利用（2D）2PCA方法对人脸的各个分块提取特征,并对各分块的特征进行加权处理,然后应用支持向量机（SVM ）实现分类识别。经过在ORL人脸库的实验研究表明,该方法压缩了人脸识别系数,缩短了识别时间,提高了识别准确率。     

一种图像压缩的改进方法

提出了一种自适应最短码长熵编码方法,用加权后的条件概率分布进行Context建模,最后用算术编码对图像进行编码,从而达到压缩效果。     

A closed-form distributed source localisation method using TDOA and GROA

This paper proposes a closed-form distributed passive source localisation method using time difference of arrival (TDOA) and gain ratios of arrival (GROA) measurements. After removing the unknown parameters in TDOA equations by using GROA measurements, the proposed method applies two-step weighted least-square (LS) minimisations. First, the TDOA and GROA equations are transformed into a set of pseudo-linear equations by introducing additional parameters, and a weighted LS estimation is used to obtain a rough estimate; secondl, this method exploits additional parameters to refine the estimate through another weighted LS estimation. The application of weighting matrix leads to an approximate maximum likelihood estimator and produces a substantial improvement in source localisation accuracy. Both the theoretical analysis and simulation results indicate that the proposed method can achieve the Cramer–Rao Lower Bound at a moderate noise level and outperform the existing methods in terms of localisation accuracy.     

非均匀噪声图像的小波去噪

目前的小波阈值去噪一般考虑单幅均匀噪声样本，针对非均匀噪声模型，提出基于邻域估计法的逐点阈值去噪算法；并将多幅均匀噪声样本的联合去噪法推广到非均匀噪声模型下。其中。阈值函数的选取是：基于信号方差和噪声方差的自适应的逐噗Bayes阈值；对多幅非均匀噪声样本采用阈值去噪与加权平均结合的方案，加权系数由各象素点的噪声方差确定，并比较了图像域和变换域两种加权方法的性能。