Multispectral image compression using eigenregion-based segmentation

In the study, a novel segmentation technique is proposed for multispectral satellite image compression. A segmentation decision rule composed of the principal eigenvectors of the image correlation matrix is derived to determine the similarity of image characteristics of two image blocks. Based on the decision rule, we develop an eigenregion-based segmentation technique. The proposed segmentation technique can divide the original image into some proper eigenregions according to their local terrain characteristics. To achieve better compression efficiency, each eigenregion image is then compressed by an efficient compression algorithm eigenregion-based eigensubspace transform (ER-EST). The ER-EST contains 1D eigensubspace transform (EST) and 2D-DCT to decorrelate the data in spectral and spatial domains. Before performing EST, the dimension of transformation matrix of EST is estimated by an information criterion. In this way, the eigenregion image may be approximated by a lower-dimensional components in the eigensubspace. Simulation tests performed on SPOT and Landsat TM images have demonstrated that the proposed compression scheme is suitable for multispectral satellite image.     

基于社交媒体的安全态势信息采集方法

本文针对社交媒体的信息安全的重要性,对已经发生的安全威胁事件及时做出反应,帮助目标用户更好的控制风险、消除安全隐患.本文以新浪微博API、网络爬虫技术、使用mmseg算法实现的jcseg分词器、JAVA正则表达式中文匹配、数据统计分析软件为基础,针对新浪微博的具有企业认证的用户的数据,进行关联相关用户、抓取数据、建立分类词库,并统计分析随时间变化的分类词库的词类、词频,对下一个时段的网络安全态势做出评估.     

脑MR图像分割和偏移场矫正的耦合水平集模型

脑核磁共振(MR)图像因需要偏移场矫正,传统分割方法很难获得准确的分割结果。针对这一问题,首先构造一组基函数拟合偏移场以保证偏移场的光滑特性,再将其融入到高斯概率密度函数中,结合统计分类准则建立脑MR图像的分割和偏移场矫正的能量方程,最后将该能量方程引入到三相位水平集的变分框架中得到脑MR图像的分割和偏移场矫正的耦合模型。实验表明该方法在得到准确的分割结果同时还可以得到较好的恢复结果。     

一种适用于室内服务机器人的实时物体识别系统

针对室内服务机器人在实际应用中的需求,提出一种结合三维点云分割和局部特征匹配的实时物体识别系统．该系统首先基于三维点云实现快速有效的物体检测,然后利用物体检测的结果定位物体在彩色图像中的区域,并采用基于SURF特征匹配的方法识别出物体的标识．实验结果表明,该系统可较好地满足室内服务机器人物体检测与识别的实时性和可靠性要求．     

在图像分割中对水平集函数应用的研究

图像分割是从图像处理到图像分析的关键技术,几何活动轮廓模型是为解决图像处理和计算机视觉领域广泛存在的图像分割问题而提出来的。水平集函数是在研究几何活动轮廓模型时将界面或者演化曲线看成高一维空间中某一函数山原型。文章在分析传统水平集函数和距离保持水平集函数优缺点的基础上,引入图像相依的权系数v（I）代替常值权系数,提出了一种自适应距离保持水平集函数。然后通过对水平集函数求其偏微分方程,经过数值实现并求出其解,从而得出图形界面的基本形状和特征。     

Efficient analysis and experimental verification of substrate‐integrated slab waveguides for wideband microwave applications

This article presents a substrate integrated waveguide, named the substrate‐integrated slab waveguide (SISW), which exhibits a wide operation bandwidth. It consists of an integrated rectangular waveguide filled with a periodically perforated dielectric medium. An efficient procedure has been developed for the calculation of the dispersion diagram of SISWs, based on the Floquet theorem, in conjunction with the segmentation technique and the boundary‐integral–resonant‐mode‐expansion (BI‐RME) method. Numerical and experimental results confirm the performance of these waveguides and the efficiency of the analysis method. © 2005 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2005.     

乘积型Otsu阈值法的快速迭代算法

针对乘积型Otsu分割准则进行阈值选取需要花费大量时间的不足,提出了乘积型Otsu阈值化分割准则的快速迭代算法。实验结果表明,本文的快速算法是有效的。     

Fast and accurate fuzzy C‐means algorithm for MR brain image segmentation

Fuzzy theory based intelligent techniques are widely preferred for medical applications because of high accuracy. Among the fuzzy based techniques, Fuzzy C‐Means (FCM) algorithm is popular than the other approaches due to the availability of expert knowledge. But, one of the hidden facts is that the computational complexity of the FCM algorithm is significantly high. Since medical applications need to be time effective, suitable modifications must be made in this algorithm for practical feasibility. In this study, necessary changes are included in the FCM approach to make the approach time effective without compromising the segmentation efficiency. An additional data reduction approach is performed in the conventional FCM to minimize the computational complexity and the convergence rate. A comparative analysis with the conventional FCM algorithm and the proposed Fast and Accurate FCM (FAFCM) is also given to show the superior nature of the proposed approach. These techniques are analyzed in terms of segmentation efficiency and convergence rate. Experimental results show promising results for the proposed approach. © 2016 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 26, 188–195, 2016     

基于Level set方法的医学图像分割

本文引入了一种基于偏微分方程的曲线进化方法—Level set方法,通过与Fast marching方法的结合,可以实现运算速度的大大提高。同时引进了更有效的Kim提出的GMM(Group Marching Method)方法,减少了运算量,并给出了改进方法。最后,把该方法用于仿真图与医学图像分割中,获得了较好的效果。     

Optimum hierarchical segmentation of OCT images in retina based on macular distance

Retina layering was the basis of optic disc structure analysis and 3D feature extraction of glaucoma.In order to improve the layering effect of retinal OCT images,an intensity based multilayer segmentation algorithm for two-dimensional retinal OCT images was proposed.Through preprocessing and filtering operation,the segmentation algorithm calculated the intensity and intensity gradient of each A-scan in the retinal OCT image to obtain the upper bound RNFL,the dividing line IS and OS,and the lower bound RPE.Then macular distance strategy,calculated by the shortest distance,was used to further optimize the layering result of macular area,so as to achieve layering segmentation of the retinal OCT images.The experimental results show the algorithm has good optimization effect,low time complexity and fast running speed.