RCAN-pytorch

这是2004年一篇重要的角点检测文献的配套Matlab源码。该算法的效果比SIFT、Harris、Susan等算法的检测效果更好。本压缩包中有从Matlab官方网站下载的源码，以及2004年那篇文献，对该算法做了详细解释。(This is 2004, an important corner detection literature supporting Matlab source code. Of the algorithm is better than SIFT, Harris, Susan, such as better detection algorithm. The compressed package from the official website to download the Matlab source code, and in 2004 came across the literature, the algorithm to do a detailed explanation.)

一种带有自适应阈值和动态支持区域的CSS角点检测算法，其效果被认为优于目前所有的CSS角点检测算法和大多数的其他类型角点检测算法。(a curvature scale space corner detector with adaptive threshold and dynamic region of support, it is considered to be the one of the best corner detection algorithms.)

说明：  多阈值的OTSU算法，用于对图像的分割。matlab语言编写。(Otsu algorithm with multiple thresholds for image segmentation)

双目立体视觉，基于matlab，适合新手看看，比较简单(Stereoscopic vision, based on matlab, suitable for novice to see)

线性变换，如图像的拉伸变换等，调试通过，简单易学(Linear transformation, such as image stretching transformation, debugging through easy to learn)

说明：  对灰度图像和二值图像进行去噪，是一种形态学滤波器。(denoiseing for the gray image and binary image)

修改了冈萨雷斯《数字图像处理》中的区域生长法。本函数中含有三种选择种子点的方法：分别依据灰度值，种子点位置，交互式选择单个种子点。(Modified the region growing method described in "Digital Image Processing" . This function contains three options for the method of seed points: based on gray value, the location of the seed points, interactive selection of a single seed point. )

说明：  在静止背景下使用背景差分法和帧间差分法进行移动目标的检测(Moving target detection using background subtraction and inter-frame subtraction in static background)

实现图像的滤波、锐化、边缘检测、微分处理及图像平滑(Image filtering, sharpening, edge detection, differential processing and image smoothing)

说明：  简单的颜色特征提取程序，可以提取RGB图像中的特征向量(Simple color feature extraction)