tuxiangpeizhun

详细介绍了K-SVD字典训练的详细过程，对稀疏表示研究很有帮助.(Detailed introduces the K- SVD dictionary of detailed training process, the sparse say that research to have the help very much. )

从一个模式识别toolbox中摘取的计算zernike不变矩的源代码，结果为图像的n阶m重zernike不变矩(From a pattern recognition toolbox extracted Zernike moment invariants calculation of the source code, the results of image re-n-order m Zernike moment invariants)

视觉仿生学在图像处理中具有非常重要的作用，视觉侧抑制原理在目标增强中具有很大的潜力(Bionics in visual image processing has a very important role in the visual principles of lateral inhibition in the target has great potential to enhance)

（1）在工具栏中点击“打开”功能出现文件打开窗口，用户选择一幅bmp图片后在指定区域居中显示该图片，若图片尺寸小于指定区域则按原始大小显示；若大于则按合适比例显示。 （2）鼠标指针在图片上停留时显示为十字形，同时在控件下方固定位置显示鼠标所在的图像x坐标和y坐标（如：50，100），以图片左上为坐标原点。 （3）在工具栏中可以点击控件实现在图片上绘制一次直线、矩形或圆等图形，在绘图过程中要求图片和图形一直可见，不能出现刷新痕迹，绘制的图形可以任意修改形状。 （4）可以任意选择图形线条的类型（虚线或直线）、颜色（三种）及粗细（三种），要求选择方式可以叠加，绘制过程要求可任意连续执行。 （5）在工具栏中点击“保存”功能出现文件保存窗口，用户可以选择保存路径来保存当前图片操作结果（包括图片和图形）。 （6）点击“关闭”功能，关闭当前图片，若操作结果尚未保存则必须弹出对话框提示用户进行保存。 ((1) in the tool bar, click on Open function has the file open window, the user selects a bmp image to center the picture in the designated area, if the image size is smaller than the specified area press the original size if more than press the appropriate scale display. (2) is shown as a cross when the mouse pointer over the image, while displaying an image x and y coordinates of the mouse cursor in a fixed position below the control (eg: 50,100) to image the upper left of the coordinate origin. (3) in the toolbar you can click controls to achieve a draw straight lines, rectangles or circles and other graphics on the picture, the requirements of pictures and graphics in the drawing process has been seen, it can not appear refreshed traces drawn graphics can be modified shape. (4) can choose the type of graph line (dashed or straight), color (three kinds) and thickness (three kinds), asked to choose the way can be superimposed, can arbitrarily draw process requires continuous exe)

基于马尔科夫随机场算法(MRF)的图像分割(Image segmentation of Markov random field algorithm)

图像盲去卷积复原程序，matlab6.5验证可以运行(image deconvolution )

图形图像处理，混合高斯图像背景估计＆更新(Graphic image processing, mixed-Gaussian background image is estimated )

一个全面的图像处理平台，基本上具有教课书上所说的所有图像处理算法，并附带一些关键算法！()

BEMD对图像进行分解 Detailed two-dimensional empirical mode decomposition (BEMD decomposition of the image)

全参考型视频质量评价方法，基于机器学习和视频特征提取，发表与2012年TMM(FR VQA method based on machine learning and video feature )