2dshangyuzhi

CVPR2013中出现的一种显著性特征检测算法，该算法用于模拟人眼视觉识别过程，提取图像中的显著性特征借后期目标对象的检测跟踪等使用，该算法(Context-Aware Saliency Detection。matlab implementation of an classical saliency detection alrogithm,which imitate our recognition process of eyes)

YUV420p图像的融合渲染，支持任意位置的融合，并支持alpha的渲染(Fusion YUV420p image rendering, support converged anywhere and supports alpha rendering)

经过改进的快速的双边滤波器算法，主要是先下采样，然后进行滤波，最后再进行上采样(Improved bilateral rapid filter algorithm is the first major down-sampling, and then filtered, and finally to the sampling)

一种改进的对比度分割算法。对红外图像有很好的分割效果。(an improved contrast ratio segmentation algorithm. The infrared image segmentation is a good result.)

这是一份关于数字图像处理半色调打印技术的MATLab源程序。(This is a paper about Halftoning.)

这是个criminisi算法的源码，可以对图像进行相应的修补。效果很好。(This is a criminisi algorithm source code, images can be appropriate patch. With good results.)

矫正桶形畸变，只是用了坐标变化，目前在研究张正友的算法，日后会上传的(correct the distortion of picture)

对图像进行傅立叶变换和反变换，计算频谱幅值(The image Fourier transform and inverse transform, the amplitude spectrum is calculated)

视觉注意力模型，寻找感兴趣区域，模仿人眼找出最感兴趣的区域，再找出第二感兴趣的区域，以此类推(Visual attention model to find the region of interest, to imitate the human eye to identify the most interesting region, and then find the second region of interest, and so on)

包含二维广义S变换程序和测试程序，用于对图像进行时频分析。matlab版本R2011b,操作系统为32位win7。在2G内存下最大只能对84*84的图像进行处理，更大的图像会出现out of memory的问题。目前网上还没有这个程序，包括本站，pudn，ilovematlab都没有。把程序上传到这三个地方，望大家一起来改进它。(Contains a two-dimensional generalized S transform procedure and testing procedure.It is used for the time-frequency analysis of images.Matlab version :R2011b, operating system: 32 win7. Tests under 2G memory can only process 84* 84 images.A larger image will incur "out of memory" problems. This program is not found online before, including this site, CSDN, ilovematlab. Upload the program to the above three websites, hoping it improved by the help of everyone.)