Techniques of Image Processing Based on Artificial Neural Networks

This paper presented an online quality inspection system based on artificial neural networks. Chromatism classification and edge detection are two difficult problems in glass steel surface quality inspection. Two artificial neural networks were made and the two problems were solved. The one solved chromatism classification. Hue, saturation and their probability of three colors, whose appearing probabilities were maximum in color histogram, were selected as input parameters, and the number of output node could be adjusted with the change of requirement. The other solved edge detection. In this neutral network, edge detection of gray scale image was able to be tested with trained neural networks for a binary image. It prevent the difficulty that the number of needed training samples was too large if gray scale images were directly regarded as training samples. This system is able to be applied to not only glass steel fault inspection but also other product online quality inspection and classification.     

基于模糊增强的图像边缘检测的研究

对图像处理时的边缘检测算法作了分析和研究,介绍了基于模糊增强的图像边缘检测算法,详细研究了单层次模糊增强和多层次模糊增强的算法,并结合实验说明,该智能图像处理方法不仅能够明显的增强图像,而且可以检测到良好的图像边缘.最后,展望了这一新的研究应用领域的发展前景.     

Studying the stability of the middle atmosphere (30―60 km) over Wuhan by Rayleigh lidar

The stability of the middle atmosphere ranging from 30 km to 60 km over Wuhan is elementarily studied, according to the observational data obtained in about one year through the WlPM Rayleigh lidar. The stability parameter （buoyancy frequency squared）, which was obtained through the temperature field, shows that the middle atmosphere over Wuhan is stable all the year round, but the stability appears variable because the stability of summer and winter is lower, and that of spring and autumn is higher.     

基于形态学的图像融合算法

提出一种基于边缘连接强度的图像融合算法。利用形态学梯度算子得到图像的边缘信息。以图像灰度的边缘连接强度加权为判据,进行图像融合。实验结果表明,该图像融合方法在保留TM多光谱图像光谱分辨率的同时,通过融合SPOT全色图像提高了空间分辨率,丰富了图像细节信息。     

数字阵列光电位置敏感器件新型结构的研究

简要阐述光电位置敏感器件的特点、工作原理,根据光电位置敏感器件的原理和光电位置方程,分析了背景光与测量精度的关系.在此基础上,采用分布图像的峰值检波器来模拟预处理光电信号,通过数字转换得到图像的重心位置;采用集中平行的模拟计算估算射到感光区的光分布的重心,并通过时钟比较器得到数字化图像.给出了检测位置的二维光传感器阵列、显示与图像数量的平方根成正比功耗关系式以及几个重要结论.     

柔性形态边缘检测算法在菌类显微图像中的应用

在灰度图像的柔性形态学概念及特性的基础上,根据菌类显微图像的边缘特点,提出了均衡化的柔性形态边缘检测方法.以霉菌图像为例,通过实验结果和传统的canny算子、LOG算子边缘提取结果进行对比,证明了算法的有效性,为菌类识别打下了良好的基础.     

大学生中跑运动员跑的技术动作分析

运用运动生理学和运动生物力学原理,借鉴国内外有关体育专家学者的研究成果,以扬州大学高水平田径队中跑训练为研究对象,结合笔者多年中跑运动训练的实践,在对现代中跑动作技术充分认识和分析的基础上,针对大学生中跑运动员训练特点与在训练中主要存在的技术问题,提出了改进技术和提高动作实效性的训练方法。     

三色Ramsey数尺（Cm1，Cm2，Cm3）研究

用r种颜色对图G的所有边着色，记着第i色的边构成的子图为G1,如果存在一种着色方法使得对所有的1≤i≤r都满足Hi￠Gi，则称图G对于（H1，H1，…．Hr）可r着色．Ramsey数尺（H1，H2，…，Hr）是使得完全图Kn对于（H1．H2，…，Hr）不可r着色的最小正整数n，令m1〉m2≥m3，Erdoes等给出了当m1足够大时R（Cm1，Cm2，Cm3）的值．通过对m1不是足够大的情况进行研究，证明了当m≥5时，R（Cm，C3m,C3）=5m=4；并给出了当m1≤7时R（Cm1，Cm2，Cm3）的值．     

墙地砖图像的快速有效提取

基于对采集到的墙地砖样本图像的特点分析，给出了墙地砖图像提取的两种思路，讨论了基于投影的边界提取和基于灰度门限的区域分割方法在墙地砖目标提取中的具体应用，选择差分投影法，完成了对墙地砖图形的有效提取，并指出了采用差分投影法进行有效目标提取应注意的问题和采取的措施。     

A New Edge-directed Subpixel Edge Localization Method

IntroductionComparedtotraditionalindustry ,microelectronicfab ricationhasthreecharacteristics :highcomplexity ,highprecisionandhighautomatization .Tomeettheprecision ,speedandreliabilityrequirements,machinevisiontech niques,suchasvisionaidedinspectionandregistration ,havebeenintroducedineveryworkingprocedureofinte grated circuitfabricationandsurfacemounttechnology(SMT) .Inspectionandregistrationprecisionmustbecon stantlyincreasedasthesizeofthecomponentbecomessmallerandsmaller .Therefore ,the…