waterline

现有自然图像素描画效果生成算法存在容易造成画面细节丢失，笔画线条单一等问题。针对这些问题，本文提出了一种改进的自然图像素描画效果生成算法，通过模拟艺术家创作素描画过程，分步生成素描画图像底纹和素描画场景笔画轮廓，采用8个方向卷积滤波提取图像中不同方向的细节信息，并使用不同长度不同粗细的笔画来模拟艺术家在创作过程中不同力度的绘画效果，最后合并素描画笔画效果和素描画图像底纹，得到与原输入自然图像内容一致，色调与艺术家绘制的素描画效果相同，笔画和底纹形式与实际素描画相似，真实感较强的素描画效果输出图像。大量实验结果表明本文方法可以生成高质量的自然图像素描画效果，与现有成熟的铅笔画生成技术相笔，本文方法具有较强的可比性。(The existing algorithms for natural image sketch production are easy to cause some problems such as the loss of image details, singleness of the stroke line. To solve these problems, this paper proposes an improved algorithm for the natural image sketch effect producing. By simulating the artist creation process of sketch, step-by-step generate image shading sketch image shading and drawing the scene outline stroke of the sketch image, using 8 directions of convolution filter to extract the details of different directions in the image, furthermore, using the stroke of different length and thickness to simulate the painting effect of different strength in the process of artist creation, finally we merge the sketch stroke effect and sketch image background to get the output image, which have consistent content with the original input image, have the same tonal effect with artists draw sketch, have the similar Stroke and background form with the actual sketch and have strong real sense in)

评估指标为点目标距离向和方位向峰值坐标、峰值旁瓣比、一维积分旁瓣比、剖面图(The evaluation indexes are peak coordinates, peak sidelobe ratio, one-dimensional integral sidelobe ratio and profile of point targets in range and azimuth directions.)

说明：  用matlab利用压缩感知CS实现对一位信号的处理~小波稀疏分解，正交追踪算法重构~1-D信号压缩传感的实现(正交匹配追踪法Orthogonal Matching Pursuit) 测量数M>=K*log(N/K),K是稀疏度,N信号长度,可以近乎完全重构(CS with matlab using compressed sensing to achieve a sparse signal processing- wavelet decomposition, the orthogonal tracking reconstruction algorithm)

红外与可见光实时融合算法 ------------------------------------ 若不能读取xvid视频，请安装XviD-1.1.3-28062007.exe。 ----------------------------------- 请双击*.bat文件看程序运行结果。 也可以在命令行下，输入“evs3 参数文件.xml 配准.xml”，以融合指定的多源视频图像。 ---------------------------------- 首先，离线地时空配准多源视频，并保存结果到xml文件。然后融合配准后的图像。融合过程是，通过分解图像为Laplacian金字塔，分别对图像的高频和低频按照规则合并，最后将Laplacian金字塔重新组合为图像。(Real time fusion algorithm for infrared and visible light------------------------------------If you cannot read XviD video, please install XviD-1.1.3-28062007.exe.-----------------------------------Double-click the*.bat file to see the program running results.Can also be in the command line, " evs3 input parameter file .Xml .Xml registration ", by the fusion of the specified source video image.----------------------------------First of all, offline space-time registration source video, and save the results to a XML file. After registration and fusion image. Through the decomposition of the image fusion process, Laplacian Pyramid, were on the high-frequency and low frequency image in accordance with the rules of the merger, Laplacian Pyramid reassembled for image.)

CBCT图像fdk重建,预投影、投影滤波、重建演示，功能强大(it s about the fdk rec for CBCT，forward projection、filter projection、rec demo)

matlab code for the v shape recognition in heart shape

关于Bayes分类器的 实验数据都有 大家相互共享 很好用的软件(Bayesian classifier on the experimental data we have very good mutual sharing of software)

这是一个关于matlab图形变化的程序，其主要有三个图形，并且能改变其颜色的程序(This program is a a matlab graphical changes, its three graphics, and can change its color program)

基于mfc对话框开发的图片位深度转换器，源码部分截图如下。 CImage img;    img.Load("D:\qrcode.png");    img.Save("D:\qrcode.bmp");    CxImage ximage;    ximage.Load("D:\qrcode.bmp", CXIMAGE_FORMAT_BMP);    ximage.AlphaStrip();    ximage.Save("D:\11.bmp", CXIMAGE_FORMAT_BMP);

1、读取显示所给PET图像（SE2IM210）。 2、学习imhist函数，画出所给PET图像的直方图。 3、根据直方图为该PET图像选择合适的显示窗（imshow参数），使胸 部轮廓等解剖结构可见。 4、根据直方图选择合适阈值，分割肿瘤区域与正常区域，计算肿瘤区 域内图像灰度均值、方差、最大值及最小值。(1 give PET images displayed, read (SE2 IM210). 2, learning, imhist function, draw the give PET image histogram. 3, according to the histogram for the PET image to choose the appropriate display window (imshow parameters), make bosom Outline of anatomical structures such as visible. 4, according to the histogram, choose appropriate threshold segmentation tumor area and normal area, calculating the tumor area In the domain of image grayscale average and variance, the maximum and minimum values.)