木马伪装技术的研究与仿真

基于当前网络安全的这种现状,我们究了当今网络上木马传播的手段和途径,并利用Vc＋＋6．0与MFC的有效结合,仿真木马常用的几种伪装技术,设计并实现了若干种木马伪装的手段：可执行文件与图片的捆绑伪装,可执行文件与．DOC文件的捆绑伪装,利用IE Dbject Data漏洞的网页进行可执行文件的传播。针对上述研究成果,描述了木马伪装的基本方法和原理,并介绍了木马伪装手段的设计与实现。     

一种边缘保持的医学图像去噪方法

医学图像去噪在图像处理中占有重要地位,对获取的医学图像进行去噪是进一步分析和计算的基础.将一维经验模式分解方法扩展到二维,提出了基于二维经验模式分解的医学图像边缘保持去噪方法.该方法先将图像进行经验模式分解,得到内蕴模式分量IMF和剩余分量,图像的噪声及边缘信息主要集中在IMF中;然后再将IMF进行经验模式分解,得到IMF的高频分量和剩余分量;最后将两次分解的剩余分量叠加,得到边缘保持的去噪图像.实验结果表明,处理后的图像较传统的医学图像去噪方法有明显的改善,在有效去噪的同时增强了边缘保护的能力.     

DirectJ: Java APIs for optimized 2D graphics

The ever more widespread diffusion of Java interfaces and animations has highlighted the performance problems of the Java graphics environment. We have analysed the bottleneck and created a set of APIs that support direct access to platform specific hardware resources for graphics acceleration. We have also re‐implemented standard APIs in order to allow transparent direct access also by programs using standard JFC. The improvement in performance of about one order of magnitude encourages the utilization of Java for realizing fluid animations on large windows. Copyright © 2001 John Wiley & Sons, Ltd.     

公路汽车视觉导航中运动目标的检测与跟踪方法的研究

通过对室外行驶车辆上所采集的长序列图象的处理与分析,研究公路汽车计算机辅助礼堂导航中运动目标的检测与跟踪问题。算法的核心是根据图象中的水平、垂直边缘及目标尾部的局部对称性检测和图象中目标的存在,进而建立描述目标与摄象机之间的相对运动的状态模型和表示目标循征的透视投影模型,应用扩展的卡尔曼滤波器进行3维运动参数估计。     

基于图像的虚拟景观漫游

提出一种基于图像的虚拟景观漫游方法。该方法采用全景图和基于图像的动画来建立虚拟环境,用户通过实时图像处理浏览器,可以模拟这两种典型的漫游行为－环绕漫游和贯穿漫游,并且在风景旅游模拟系统（Virtrual-Touring)中实现了这种方法。     

浅谈实现建模技术的三种方法

建模技术是虚拟实现中的技术核心,尤其是图象的建模技术是当今虚拟现实建模技术研究的热点,也是未来几年重点的研究方向,目前主要有三种方法实现。     

基于改进YOLOv5的荧光图像细胞智能检测研究

为解决人工对荧光原位杂交(Fluorescence In Situ Hybridization, FISH)荧光图像进行结果判读存在的效率低、劳动强度大等问题,针对FISH荧光图像细胞智能检测提出一种融合空域图像增强的改进YOLOv5算法。算法在原始YOLOv5神经网络模型基础上,加入了空域图像增强模块,并选择了模块最佳增强系数,扩大了模型对荧光图像的对比度适应范围,提高了模型的特征提取能力和细胞检测准确率。实验结果显示,改进YOLOv5模型的平均精度均值(Mean Average Precision, mAP)为0.983,达到了比原始模型更优的训练效果和收敛速度,并且,改进YOLOv5模型的细胞识别率达到91.65%,比原始YOLOv5模型提升了9.19%。将细胞智能检测算法嵌入自主开发的荧光图像智能检测软件,结合荧光点检测算法,可给出有效判读结果。     

基于不规则尺度区域光谱信息的高光谱图像亚像元定位（英文）

亚像元定位技术可以分析混合像元,并实现从丰度图像到亚像元级精细土地覆盖定位图像的转换。然而,传统的亚像元定位方法所使用的光谱信息通常在指定的矩形局部窗口中构造,并且很少使用所有波段的光谱信息,影响了亚像元定位的性能。为了解决这一问题,本文提出了一种基于不规则尺度区域光谱信息的高光谱图像亚像元定位方法 （SIISA）。在三幅遥感图像上的实验结果表明,所提出的SIISA优于现有的亚像元定位方法。     

Dual-branch deep image prior for image denoising

In this work, we propose a two-stage denoising approach, which includes generation and fusion stages. Specifically, in the generation stage, we first split the expanding path of the UNet backbone of the standard DIP (deep image prior) network into two branches, converting it into a Y-shaped network (YNet). Then we adopt the initial denoised images obtained with DAGL (dynamic attentive graph learning) and Restormer methods together with the given noisy image as the target images. Finally, we utilize the standard DIP on-line training routine to generate two complementary basic images, whose image quality is quite improved, with the help of a novel automatic iteration termination mechanism. In the fusion stage, we first split the contracting path of the standard UNet network into two branches for receiving the two basic images generated in the previous stage, and obtain a fused image as the final denoised image in a fully unsupervised manner. Extensive experimental results confirm that our method has a significant improvement over the standard DIP or other unsupervised methods, and outperforms recently proposed supervised denoising models. The noticeable performance improvement is attributed to the proposed hybrid strategy, i.e., we first adopt the supervised denoising methods to process the common content of images substantially, then utilize the unsupervised method to fine-tune the specific details. In other words, we take full advantage of the high performance of the supervised methods and the flexibility of the unsupervised methods.