DLA

介绍了一种显著性检测，程序可以直接运行，可以得到显著图像，有图像源。(propose a bottom-up visual saliency detection algorithm. Different most previous methods that mainly concentrate on image object, we take both background and foreground into consideration. )

说明：  SIFT特征点的提取和匹配，SIFT算法首先在尺度空间上进行关键点检测，确定关键点的位置和关键点所处的尺度，然后使用关键点邻域梯度的主方向作为该点的方向特征，最后由关键点邻域梯度信息生成关键点的特征向量(SIFT algorithm firstly detects the key points in the scale space, determines the location of the key points and the scale of the key points, then uses the main direction of the key point neighborhood gradient as the direction feature of the point, and finally generates the feature vector of the key points from the key point neighborhood gradient information)

易语言2D游戏引擎模块源码，易语言写的图形图象编程源码，很好的参考。(Easy language 2D game engine source module, easy language to write the graphics programming source code, a good reference.)

计算机图形学中小例子，MFC下实现Sutherland_Cohen直线段裁剪算法(Computer graphics small example)

说明：  基于相位梯度法PGA的 Matlab 估计相位误差 估计多普勒中心(Estimation of Phase Error and Doppler Center by PGA MATLAB)

Transferring color to greyscale images的原文及源代码，包括详细的测试图像以及相应的论文及源代码，是学习图像色采转移必看的经典内容。(Transferring color to greyscale images of the original text and source code, including detailed test image and the corresponding papers and source code is studying the image to see the classic color adopted transfer content.)

一种中值滤波的改进方法，基于滤波窗口邻域权重的中值滤波。(A median filter improvement method, based on filtering window neighborhood the weights of the median filter.)

基于纹理和边缘方向特征融合的目标跟踪程序代码，是基于mean shift框架的(This paper proposes a powerful and robust local descriptor,called textureorientation descriptor(TOD). TOD consists of two components: texture and orientation. Considering that the human shape shows more short, fragmentary and vertical edges, the proposed TOD descriptor encodes the spatial information of pedestrian image. We combine the proposed TOD representation model with mean shift framework to perform pedestrian tracking. Results from experiments show the improved performance of the proposed algorithm, in the scenarios of heavy occlusions, illumination variations and similar objects interference, when compared with the other descriptors based trackers.)

双目视觉经验总结，希望后面的不要犯错误。(Binocular visual experience summary, make no mistake behind.)

说明：  Matlab代码文字识别：包括图像分割,粘连字符切分,文字识别(Using MATLAB to realize the code of recovering scene view distance map (depth map) from binocular map)