小样本训练集下人脸图像超分辨率重构算法

文章提出了一种针对小样本训练集的人脸图像超分辨率重构算法.该算法在马尔可夫网络模型的基础上,将视觉相容性检查准则引入到候选分块的匹配准则中,提高了匹配精度和块间兼容性.将权值机制融合进图像的重构过程,强化了训练集的有用性.实验表明,在小样本训练集下,算法能有效地抑制块效应和局部失真现象,明显改善超分辨率图像的质量.     

基于稀疏表示的图像超分辨率算法

基于稀疏表示的超分辨算法能有效地解决单幅图像的超分辨的问题,得到的超分辨结果比较理想。在此方法基础上,MichaefElad进行了改进和完善,在基于稀疏表示的基础上,提出一种新超分辨算法。本文提出～种改进方法,在Elad的方法的基础上,通过利用PCA主成分分析方法,进而减少运算量,借助K—SVD算法对原子库进行相应的训练,算法速度提高,取得较好的超分辨结果。借助误差反投影方法,优化超分辨结果。     

多帧超分辨率图像重建迭代小波算法研究

为了解决由于物体的运动和拍摄环境等因素,造成拍摄后多帧图像分辨率低和细节丢失的问题。本文对现有超分辨图像处理算法查阅研究,提出超分辨率图像重建迭代小波算法。最终对比迭代小波算法运算后最终的图像和参考帧图像,并比较图像信噪比的变化得出迭代小波算法的优越性。     

基于张量投票的图像超分辨率算法

张量投票算法在提取图像主观轮廓上具有良好的效果。文章提出了一种基于张量投票的图像超分辨率算法。首先,用二维张量矩阵存储低分辨率图像各像素点所处的位置特征信息,并利用稀疏张量投票将特征信息进行加强,再使用稠密张量投票产生高分辨率图像对应的二维张量矩阵,此张量矩阵包含了视觉特性强的边缘信息,最后利用该边缘信息指导高分辨率图像的重构。实验结果表明,该方法得到的高分辨率图像信噪比高、视觉效果好。     

基于张量投票的图像超分辨率算法

张量投票算法在提取图像主观轮廓上具有良好的效果。文章提出了一种基于张量投票的图像超分辨率算法。首先,用二维张量矩阵存储低分辨率图像各像素点所处的位置特征信息,并利用稀疏张量投票将特征信息进行加强,再使用稠密张量投票产生高分辨率图像对应的二维张量矩阵,此张量矩阵包含了视觉特性强的边缘信息,最后利用该边缘信息指导高分辨率图像的重构。实验结果表明,该方法得到的高分辨率图像信噪比高、视觉效果好。     

视频图像超分辨率应用系统设计与实现

文章设计实现了一个视频图像超分辨率应用系统,描述了超分辨率实验平台的设计,包括系统结构、图像与视频内容、主要算法模块设计,介绍了开发该系统的平台、开发该平台所使用的关键技术,给出了使用本系统处理后的图像,并对处理后的图像进行了主观评价。     

小样本条件下的煤矿安全评价方法研究

研究煤矿安全评价问题的现状,针对传统的BP神经网络要获得可信度较高的评价模型需要大量的样本进行学习的缺点,采用V-fold Cross-validation技巧,利用MATLAB神经网络工具箱,建立基于BP神经网络的煤矿安全评价模型,利用实际指标数据研究小样本条件下的煤矿安全评价,并验证评价效果的有效性.     

一种基于小波神经网络的超分辨图像重构

针对在航空航天遥感领域中使用的CCD相机对景物进行成像时,由于像元尺寸的限制导致图像低分辨率的问题和传统的图像重构算法的不足,提出了小波神经网络映射图像重构过程非线性特性的方法。实验表明,用小波神经网络对低分辨的图像重构,可以得到高分辨率图像。通过仿真实验得到高分辨率和高信噪比的超分辨结果：     

小样本条件下的煤矿安全评价方法研究

研究煤矿安全评价问题的现状,针对传统的BP神经网络要获得可信度较高的评价模型需要大量的样本进行学习的缺点,采用V—fold Cross—validation技巧,利用MATLAB神经网络工具箱,建立基于BP神经网络的煤矿安全评价模型,利用实际指标数据研究小样本条件下的煤矿安全评价,并验证评价效果的有效性。     

基于L1-L2混合噪声模型的图像超分辨率重建方法

文章提出了一种基于L1-L2混合噪声模型(HNM)方法用于图像、视频的超分辨重建,该方法有效利用L1范数在突变区域较好保持图像边缘信息的特点,同时兼顾了L2范数对图像平坦区域的噪声抑制特性。针对求解过程中噪声分布的改变,L1、L2范数的选择问题,提出一种自适应隶属度(AMD)方法,该方法不仅能达到理想的实验效果,而且大大地减少了迭代次数与运算时间。     

Linking of sample data to small areas

We consider methods for estimating the means of survey variables in domains of a finite population, where sample sizes are too small to obtain reliable direct estimates. We construct generalized compositions from the direct and traditional design-based synthetic estimators and propose the methodology for evaluating their coefficients. This methodology measures similarities among sample elements and estimates of the domain means. We propose the compositions for two cases of auxiliary information: domain-level characteristics are available; true means of auxiliary variables are available for the estimation domains, and unit-level auxiliary vectors are known for the sample elements. In the simulation study, we show where the generalized compositions improve the traditional synthetic and composite estimators.     

重构小城镇社会结构的实证研究——以临安市地名规划中的民意差异为例

快速推进的城市化改变了小城镇原有的人口结构,其人口特征的异质性明显增强,不同人口群体的社会要求也日见多样化,社会整合压力日益突出。为确保小城镇和谐发展,需要重构其固有的社会结构,重构的起点是破除已经结构化了的利益群体生成和维护机制;重构的措施包括尊重并提升小城镇后来人口的社会利益,协调城市固有人口的利益差异,建构开放性的、常规化的社会成员交流与沟通平台和管道;重构的目的是实现小城镇增容、扩面与和谐发展的同步与同构。     

烘炒食品卫生标准检验方法中样品制备方法的探讨

在烘炒食品检验时,对用样品去壳处理与非去壳处理两种制备的方法进行过氧化值的试验,通过样品不同浸泡时间酸价的测定试验,得出了样品处理可考滤直接制样而不去壳,提取油脂的时间应是浸泡8～18h的结论。     

General conditions for the existence of maximal elements via the uncovered set

This paper disentangles the topological assumptions of classical results (e.g.,Walker, 1977 on the existence of maximal elements from rationality conditions. It is known from the social choice literature that under the standard topological conditions—with no rationality assumptions on preferences—there is an element such that the upper section of strict preference at that element is minimal in terms of set inclusion, i.e., the uncovered set is nonempty. Assuming the finite subordination property, a condition that weakens known acyclicity and convexity assumptions, each such uncovered alternative is in fact maximal. Implications are a generalization of a result of Yannelis and Prabhakar (1983) on semi-convexity, an extension of Fan’s (1961) lemma on KKM correspondences, and the existence of fixed points for subordinate convex correspondences generalizing the work of Browder (1968).     

内陆城市空间视觉形象设计分析

从城市空间与形态、城市道路、城市中心区、城市工业区、城市社区、城市广场、建筑及城市天际轮廓线七个方面探讨了内陆城市空间视觉形象存在的问题及改进措施.     

小城镇可持续发展的资金筹措

作者论述了小城镇可持续发展的资金来源渠道 ,指出建立一套地方的“自我造血机制” ,才是保证可持续发展的根本。     

A generalization of the indiscernibility relation for rough set analysis of quantitative information

Rough set theory is a formal tool for analysis of knowledge gained by experience. The knowledge is represented by a data set organized in a table called information system. Rows of the table correspond to objects and columns to attributes. The idea of the rough set consists in approximation of a set of objects by a pair of sets called lower and upper approximation. The definition of the approximations follows from an indiscernibility relation between objects. Objects are described by attributyes of qualitative or quantitative nature. In the case of quantitative atrributes, the indiscrenibility relation has been defined after partition of the real scale into a finite number of intervals. The bounds of the intervals are more or less arbitrary and may influence the result of the rough set analysis. In order to capture this influence, we consider overlapped intervals and introduce for them a strict and a weak indiscernibility relation. Then, we generalize the lower and upper approximations, the measures of the quality of approximation and the concept of decision rules.

---

Riassunto Nella teoria degli insiemi apprissimati, la relazione di indiscemibilità trao oggetti costituisce il punto di partenza della definizione della coppia di insiemi, chiamati rispettivamente approssimazione superiore ed inferiore, che caratterizzano ciascun insieme. Se gli oggetti sono descritti mediante atributi di natura quantitativa, occorre suddividere il dominio di ciascuno di questi in sottointervalli, mediante l'introduzione di opportuni confini. Per analizzare l'effetto dell'arbitrarietà della scelta di tali valori, si introducono delle soglie additive e si considerano le zone di sovrapposizione di tali sottointervalli, definendo opportunamente relazioni di indiscemibilità forte e debole. Siggene ralizzano quindi i concetti di approssimazione superiore ed infereiore, gli indicaartori della qualità dell'approssimazione e le regole decisionali stesse, fornendone un'esemplificazione applicativa.

     

A consistent test for nonlinear out of sample predictive accuracy

In this paper, we draw on both the consistent specification testing and the predictive ability testing literatures and propose an integrated conditional moment type predictive accuracy test that is similar in spirit to that developed by Bierens (J. Econometr. 20 (1982) 105; Econometrica 58 (1990) 1443) and Bierens and Ploberger (Econometrica 65 (1997) 1129). The test is consistent against generic nonlinear alternatives, and is designed for comparing nested models. One important feature of our approach is that the same loss function is used for in-sample estimation and out-of-sample prediction. In this way, we rule out the possibility that the null model can outperform the nesting generic alternative model. It turns out that the limiting distribution of the ICM type test statistic that we propose is a functional of a Gaussian process with a covariance kernel that reflects both the time series structure of the data as well as the contribution of parameter estimation error. As a consequence, critical values that are data dependent and cannot be directly tabulated. One approach in this case is to obtain critical value upper bounds using the approach of Bierens and Ploberger (Econometrica 65 (1997) 1129). Here, we establish the validity of a conditional p-value method for constructing critical values. The method is similar in spirit to that proposed by Hansen (Econometrica 64 (1996) 413) and Inoue (Econometric Theory 17 (2001) 156), although we additionally account for parameter estimation error. In a series of Monte Carlo experiments, the finite sample properties of three variants of the predictive accuracy test are examined. Our findings suggest that all three variants of the test have good finite sample properties when quadratic loss is specified, even for samples as small as 600 observations. However, non-quadratic loss functions such as linex loss require larger sample sizes (of 1000 observations or more) in order to ensure reasonable finite sample performance.     

适用于中小型企业的自动称重系统的研制

本文对研制适用于中小型企业的自动称重系统的背景和意义进行了阐述,然后对国内外研究现状进行了描述,之后给出了研究内容和技术关键,最后给出了技术方案、技术路线及可行性分析。