Image processing using cellular neural networks based on multi-valued and universal binary neurons

Multi-valued and universal binary neurons (MVN and UBN) are the neural processing elements with the complex-valued weights and high functionality. It is possible to implement an arbitrary mapping described by partially defined multiple-valued function on the single MVN. An arbitrary mapping described by partially defined or fully defined Boolean function, which can be non-threshold, may be implemented on the single UBN. The quickly converging learning algorithms exist for both types of neurons. Such features of the MVN and UBN may be used for solving the different problems. One of the most successful applications of the MVN and UBN is their usage as basic neurons in the Cellular Neural Networks (CNN). It opens the new effective opportunities in nonlinear image filtering and its applications to noise reduction, edge detection and solving of the super resolution problem. A number of experimental results are presented to illustrate the performance of the proposed algorithms.An erratum to this article can be found at     

Variations in Spectral Slope in Lake Taihu,a Large Subtropical Shallow Lake in China

Spectral slope (S), describing the exponential decrease of the absorption spectrum over a given wavelength range, is an important parameter in the study of of chromophoric dissolved organic matter (CDOM) dynamics, and also an essential input parameter in remote sensing models. Furthermore, S is often used as a proxy for CDOM composition, including the ratio of fulvic to humic acids and molecular weight. The relative broad range in S values reported in the literature can be explained by the different spectral ranges and fitting methods used. A single exponential model is used to fit the S values for 17 investigations involving 458 samples in Lake Taihu from January to October in 2004. The average S value was 15.18 ± 1.39 μm⁻¹ for the range of 280–500 nm, which fell within the range reported in the literature. The frequency distribution of S value basically obeyed a normal distribution. Significant differences in S values between summer and other seasons showed that phytoplankton degradation was one of the important sources of CDOM in summer, whereas CDOM mainly came from the river input in other seasons. Furthermore, the estimated S value decreased with increasing wavelength range used in regression. The maximum and minimum values derived from the regression were 17.89 ± 1.25 μm⁻¹ and 13.62 ± 2.11 μm⁻¹ for the wavelength ranges of 280–380 nm and 400–500 nm, respectively, a decrease of 23.9%. S values significantly decreased with the increase of CDOM absorption coefficients. CDOM absorption coefficients could be more appropriately estimated from exponential model introducing the variation of S with absorption coefficients, making them useful for a remote sensing bio-optical model of Lake Taihu. DOC-specific absorption coefficient a*(λ) and the parameter M describing molecular size of the humic molecules could also be used as a proxy for the sources and types of CDOM. A general relationship was found between S and a*(λ), and M values. S increased with the decrease of DOC-specific absorption coefficient and the increase of M corresponding to the decrease of molecular weight.     

Monitoring slope deformation using a 3-D laser image scanning system:a case study

An ILRIS-36D 3-D laser image scanning system was used to monitor the Anjialing strip mine slope on Pingshuo in Shanxi province.The basic working principles,performance indexes,features and data collection and processing methods are illustrated.The point cloud results are analyzed in detail.The rescale range analysis method was used to analyze the deformation characteristics of the slope.The results show that the trend of slope displacement is stable and that the degree of landslide danger is low.This work indicates that 3-D laser image scanning can supply multi-parameter,high precision real time data over long distances.These data can be used to study the distortion of the slope quickly and accurately.     

图像阈值自动选取算法的C＋＋实现

图像分割是运动目标检测与跟踪技术必须要解决的问题,在很多时候它涉及到图像阈值的选取。文章采用的算法首先计算图像中不同区域的灰度均值,结合最小差值条件,反复修订由计算所得的阈值,从而达到自动选优的目的。在此基础上,文章进一步给出了用C＋＋语言实现算法的关键代码。测试表明此方法选择阈值简便实用,图像的二值化效果良好。     

运动汽车图像静态视点平滑特征优化仿真

由于运动汽车图像在特征采集过程中,汽车处于高速运动状态,采集的过程无法与汽车完全同步,造成汽车的特征像素分量在高速运动中丢失,产生较大的像素运动噪声,使得汽车图像边缘高频特征因为运动干扰而模糊.传统的平滑过渡方法在对运动汽车图像进行平滑处理时,按照图像中像元灰度值计算突变特性,但受到像素丢失与噪声无法抑制的影响,无法解决运动汽车图像高频分量对图像像元灰度值的干扰问题.提出基于替身运动DR算法的运动汽车图像静态视点平滑过渡方法,用替身像素描述汽车在场景中的运动特征,替身像素在场景中运动并同其它汽车的替身进行交互,采用局部化的车辆模型提高运动汽车场景的逼真度,通过依据替身运动的平滑过渡算法完成归一化线性运动汽车图像静态视点的平滑过渡,解决了运动汽车图像的平滑过渡问题.实验结果说明,所提方法可确保运动汽车图像边缘锐化,有效处理平滑噪声和锐化边缘.     

陈毅诗词夜意象的探析

作为一种文学意象,“夜”经常出现在陈毅诗词中。在陈毅诗词中,由于创作时代背景和诗人创作心理,“夜”不仅是时空概念,更赋予了紧张战斗、自由思想、欢乐工作的丰富内涵,具有独特的表现特征和审美价值。通过对陈毅诗词夜意象的探析,可以探究陈毅诗词的艺术价值。     

图像处理建立混凝土有限元模型探讨

针对工程中常用的混凝土材料的不均匀特性,提出了一种基于图像处理技术建立二维混凝土有限元模型的方法.该方法综合图像处理过程中的图像增强、消除噪声和边缘检测技术建立人机对话平台,并结合网格自动划分技术建立非均匀有限元模型.通过一个实例,验证了该方法的有效性.     

城市街区空间引导系统的设计思考

城市街区空间引导系统与人们的日常生活息息相关,为人们的出行提供了便捷的标识引导,同时它也是城市形象的重要组成部分之一。本文分析总结了该系统的设计原则,并从视觉传达学科入手分析其视觉元素的设计。为了设计无语言障碍和有个性、地域化的城市街区空间引导系统,从符号、文字、色彩三方面对其进行设计思考。     

基于CBS模式的档案管理数字化系统的研究

随着我国经济和社会的飞速发展.人民对信息的要求日益提高.档案管理在这种新的形势下.面临巨大的挑战.传统的档案管理已经不能适应新形势的发展,档案管理数字化系统进行研究势在必行.本文主要对档案管理的涵义、数字化系统方案设计.文档图像处理和系统软件部分等进行了相应的阐述.本文的研究对以后指导档案管理工作具有一定的理论意义和现实意义.