Effective optic disc detection method based on swarm intelligence techniques and novel pre-processing steps

Diabetic retinopathy affects the vision of a significant fraction of the population worldwide. Retinal fundus images are used to detect the condition before vision loss develops to enable medical interventions. Optic disc detection is an essential step for the automatic detection of the disease. Several techniques have been introduced in the literature to detect the optic disc with different performance characteristics such as speed, accuracy and consistency. For optic disc detection, a nature-inspired algorithm called swarm intelligence has been shown to have clear superiority in terms of speed and accuracy compared to traditional detection algorithms. We therefore further investigated and compared several swarm intelligence techniques. Our study focused on five popular swarm intelligence algorithms: artificial bee colony, particle swarm optimization, bat algorithm, cuckoo search and firefly algorithm. This work also featured a novel pre-processing scheme that enhances the detection accuracy of the swarm techniques by making the optic disc region the highest grayscale value in the image. The pre-processing involves multiple stages of background subtraction, median filtering and mean filtering and is named Background Subtraction-based Optic Disc Detection (BSODD). The best result was obtained by combining our pre-processing technique, firefly algorithm and the parameters used for the algorithm. The obtained accuracy was superior to the other tested algorithms and published results in the literature. The accuracy of the firefly algorithm was 100%, 100%, 98.82% and 95% when using the DRIVE, DiaRetDB1, DMED and STARE databases, respectively.     

一个基于Java的可视化挖掘工具的设计和实现

介绍了一个可视化挖掘工具,给出了其框架体系结构,并主要从数据挖掘技术、数据视图及其操纵界面技术、系统安全性三个方面作了介绍。     

A neural network to predict attendance of paediatric patients at outpatient clinics

The development of a feed-forward neural network to predict attendance and non-attendance at a hospital outpatient clinic is described. Particular emphasis is given to the post-processing applied to the network output, and to the choice of information presented to the network. The effect of individual inputs on the performance of the network is examined, and two methods of dealing with the problem of ambiguous input data are explored. It is shown that good results (approximately 90% accuracy) are achieved with a feedforward network — having 15 input nodes, a single hidden layer of five nodes and one output node with supervised backpropagation — even where data is limited, and that an understanding of the problem can lead to the modification of standard procedures and improved network performance.     

一种改进的人脸图像检测与识别中的预处理方法

在局部二值化基础上采用了基于灰度比对、对称相似度测量和方差投影相结合的方法进行人脸预处理,改进了对称相似度测量的具体实现方法,并与几何归一化交叉进行。改进后的方法在保证速度的前提下增强了系统的适用范围,特别是对大角度倾斜的人脸预处理更具优势。     

广义模糊算子法用于图象的浮雕显示

广义模糊算子法是一种用于图象边缘检测的全新而有效的方法。它能与不同的图象预处理方法相结合从而产生不同的图象显示效果。此文提出一种预处理方法，首先对一幅图象进行预处理，然后将广义模糊算子作用于该图象，能得到较好的浮雕显示效果。调整预处理中的参数，所显示的效果也有所不同。     

试井中压力测试数据的处理方法研究

本文研究了试井中压力测试数据的预处理方法。通过信号编排，Ｋａｌｍａｎ滤波，Ｂ样条函数拟合，可以获得测试时间内任一点的压力和压力导数值。两个实例显示了该方法的特性     

基于NIOSII指纹采集系统设计与实现

本文以嵌入式应用为背景,提出了一种基于NIOSII的指纹采集系统设计方案,给出了该系统的硬件设计结构和软件算法,并利用NIOSII定制指令来加速实现指纹图像预处理算法。实验结果表明,该系统能够有效采集指纹数据,实时处理并获取指纹有用信息,提高指纹图像增强的效果和速度。     

基于ARM9的嵌入式指纹图像处理算法研究

随着指纹识别技术的发展和嵌入式系统的广泛应用,指纹识别逐渐向嵌入式方向发展。针对ARM9嵌入式开发平台,提出了一种适合于嵌入式系统的指纹图像预处理算法。该算法改进了传统的Gabor增强,消除了奇异点处脊线断裂和错连的问题,并采用了复合细化算法对二值图像进行细化以及细化去噪处理。实验表明,该算法具有良好的实用性和快速性,满足了嵌入式指纹识别系统的要求。     

FY-3气象卫星MERSI数据快速预处理的IDL实现

作为新型卫星数据源,FY\|3/MERSI(风云三号中分辨率光谱成像仪)影像的快速预处理方法与模块目前较少见。采用基于三角网的几何校正算法,根据研究区Shapefile文件和FY\|3/MERSI自带定位数据提取处理区域,实现对应区域全部20个通道几何校正,并利用后向映射重采样输出各通道图像纠正后像元点DN值,随后进行辐射定标、太阳高度角订正等预处理。该系列过程用IDL编写相关程序实现了用户界面化交互操作。运行结果表明:设计的算法流程占用内存小,计算速度快。对于一个面积约45万km²的区域,所有通道处理耗时仅450 s,且校正后影像质量和精度均较好。相较于相同区域借助ENVI软件下地理位置查找表法(GLT)仅实现单通道几何校正耗时超30 min,本文开发的模块大大提高了FY\|3/MERSI数据处理效率,为其在城市热环境、积雪等领域的应用做好准备工作。