1-s2.0-S0925753510002559-main.pdf

一款完全免费的专业级屏幕捕捉软件，能够让您得心应手地捕捉到需要的屏幕截图。捕捉图像方式灵活，主要可以捕捉整个屏幕、活动窗口、选定区域、固定区域、选定控件、选定菜单、选定网页等，图像输出方式多样，主要包括文件、剪贴板、画图和打印机。软件具有捕捉光标、设置捕捉前延时、显示屏幕放大镜、自定义捕捉热键、图像文件自动按时间或模板命名、捕捉成功声音提示、重复最后捕捉、预览捕捉图片、图像打印、图像裁切、图像去色、图像反色、图像翻转、图像旋转、图像大小设置、常用图片编辑、墙纸设置等功能。捕捉到的图像能够以保存图像文件、复制到剪贴板、输出到画图、打印到打印机等多种方式输出。 (A completely free professional screen capture software that allows you to be able to adequately capture the need for a screenshot. A flexible way to capture the image, the main can capture the entire screen, active window, selected regions, fixed region, the selected control, the selected menu, select Web pages, images, various output methods, mainly including documents, clipboard, drawing and printers. Software has to capture the cursor, set the delay before the capture, display screen magnifier, custom capture hotkeys, image file names automatically by time or templates to capture the success of the voice prompts, repeat last capture, preview captured pictures, image print, image cut , the image to the color, the anti-color images, image flip, image rotation, image size setting, commonly used photo editing, wallpaper settings and other functions. Images can be captured to save the image file, copy to the clipboard, export to the drawing, print to a printer output of a variety of ways)

模式识别的Sobel和Kirsch边缘检测程序(Sobel and Kirsch edge detection algorithm of Pattern recognition)

GraphCut算法的实现，跟踪主动镜头下的目标，效果很好！(GraphCut algorithm to track the goal of the initiative under the lens, very good!)

说明：  VC bmp图像数据读取和输出代码程序,经过编译可行(compiled vc program in reading image )

利用位图图像中的冗余数据位，将小文件嵌入到大的图像文件中，并保持原图像不变。(The use of bitmap images in the redundant data bit will be embedded in small files to large image files, and to maintain the original image unchanged.)

船舶数据处理程序，可以实现船舶任意运动姿态的数据，描绘运动轨迹，从而分析船舶运动姿态(ship data extraction)

RAw格式图片的显示，边缘检测，包括SOBEL算子，具有不同模板的拉普拉斯算子边缘检测，以及一些简单的滤波方式(sadfsadf asdfasdf asdf)

三维激光点云配准是点云三维建模的关键问题之一。经典的 ICP 算法对点云初始位置要求较高且配准 效率较低，提出了一种改进的 ICP 点云配准算法。该算法首先利用主成分分析法实现点云的初始配准，获得较好 的点云初始位置，然后在经典 ICP 算法的基础上，采用 k － d tree 结构实现加速搜索，并利用方向向量夹角阈值去除 错误点对，提高算法的效率。实验表明，本算法流程在保证配准精度的前提下，显著提高了配准效率。 (Three-dimensional laser point cloud registration is one of the key three-dimensional point cloud model. High classical ICP algorithm to the initial position of the point cloud registration requirements and low efficiency, proposed an improved ICP point cloud registration algorithm. Firstly, the use of principal component analysis of the initial point cloud registration, get a better initial position of the point cloud, then the basis of classical ICP algorithm using k- d tree structure to achieve speed up the search, and using the direction vector angle the removal of the threshold point error and improve the efficiency of the algorithm. Experiments show that the algorithm processes to ensure the accuracy of registration under the premise, significantly improve the efficiency of registration.)

Shap Context based Shape recognition

说明：  bitMAP文件格式的图像的读取、与保存的算法，可以作为图像处理的系统的前道，非常实用。(bitMAP file format of the image read, and preservation of the algorithm, as image processing system of the former Road, very practical.)