region-merging-RAG

matlab工具箱，用于构建和重建可分离的正交可操纵金字塔。(a matlab toolbox for building and reconstructing separable quadrature steerable pyramids.)

基于模糊对比度的图像增强方法，大致过程仍然是先把图像从空间域映射到模糊域，在模糊域内通过定义一个局部对比度算子，然后通过对凸函数的加强来放大像素邻域的各像素之间的差异。 (Based on the fuzzy contrast image enhancement method, the general process is still the first images from space domain is mapped to the fuzzy field in fuzzy field through the define a local contrast operator, and then the convex function to enlarge the strengthening of pixels each neighborhood pixel differences. )

图像检测的算法，Faster R-CNN算法，先对整张图像进行卷积计算，然后通过感兴趣区域池化层(RoI Pooling Layer)将选择性搜索算法推荐出来的候选区域和卷积网络计算出的特征映射图进行融合，得到候选区域对应的特征矢量，这种共享卷积计算的操作极大地减少了卷积计算的次数。而且这些特征矢量的维度统一，方便后续的分类工作。通过感兴趣区域池化层处理卷积特征，并将得到的特征送往两个并行计算任务进行训练，分类和定位回归。通过这些方法和改进的框架，Fast R-CNN 用更短的训练和测试时长，取得了比 R-CNN 更好的效果(Faster R-CNN algorithm first convolutes the whole image, then fuses the candidate regions recommended by the selective search algorithm and the feature mapping maps calculated by the convolution network through the RoI Pooling Layer to get the corresponding feature vectors of the candidate regions, which greatly reduces the number of convolution calculations. Moreover, the dimension of these feature vectors is unified, which facilitates the subsequent classification work. The convolution feature is processed by the pooling layer of the region of interest, and the obtained feature is sent to two parallel computing tasks for training, classification and positioning regression. Through these methods and improved framework, Fast R-CNN uses shorter training and testing time and achieves better results than R-CNN.)

SURF算法较SIFT算法速度快，SURF算法源代码。(SURF code)

本代码主要给出了激光粒度仪颗粒散射光强分布以及4种粒度反演算法，以及4种算法之间的比较。四种反演算法为：TSVD、Chaine、Tikhonov和l1正则化。(The code gives the Zetasizer particle scattering intensity distribution, and four kinds of particle inversion algorithm, as well as a comparison between the four algorithms. Four kinds of inversion algorithm is: TSVD, Chaine, Tikhonov and l1 regularization.)

CBIR系统中采用的tamura纹理特征计算程序(Tamura texture features used in CBIR system calculation program)

图像融合里边剪切波变换方法的工具箱，欢迎下载(Shear wave transformation method for image fusion in the toolbox, welcome to download)

图像变形处理程序，VC2013+opencv实现，利用三种差之方法扭曲变形( Image deformation processing program, VC2013+ opencv realized the difference between using three methods distorted)

基于改进的F-S error diffusion算法对彩色图像位数降为8色。其中分配系数采用动态系数(Based on the F-S error diffusion algorithm to improve the color image figures down to 8 colors. The distribution coefficient by using the dynamic coefficient)

说明：  双目视觉导航的文章，介绍了CCD标定，图像匹配，三维重建等关键技术(TE PLEASE DOWNLOAD IT )