3D_Moment_Invariant

给出了偏微分方程的径向基函数配点法的数值解法，进行了数值模拟，并且给出了图形(The numerical solution of the radial basis function with partial differential equation method, numerical simulation, and gives the graphic )

人工智能 caffe 用与ssd yolo(Artificial intelligence SSD Yolo)

blkproc.m,DCHuffmanEncoding.m,ACHuffmanEncoding.m,zigzag.m,PSNR.m, 对灰度图像进行DCT变换,量化,ZigZag扫描,Huffman编解码,反量化,反DCT变换而重建图像。 其中，blkproc.m为分块DCT变换函数； DCHuffmanEncoding.m，ACHuffmanEncoding.m分别为DC和AC变换系数的Huffman码表函数； zigzag.m为ZigZag扫描函数；PSNR.m为求图像峰值信噪比函数。 Copyright 2008 Reserved @ Wang Chengyou @ Tianjin University, P.R.China. (This function tests the DCTJPEG codec)

说明：  一种改进的均值聚类算法，能很好的利用与图像分割技术(k-means cluster)

基于熵率的超像素分割，图像处理，图像分割技术(superpixel segmentation based on entropy rate, image processing, image segmentation technology)

快速k-means算法,比matlab 自带的要快很多,不错的源码(K- means algorithm quickly, much faster than with matlab, good source)

zemax非序列下gaussian光束的matlab程序（包括zemax演示源文件）(zemax sequence under non-gaussian beam matlab program (including zemax demo source files))

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.)

本rar文件是图像超分辨率重构的网络模型RCAN的代码，可以成功运行(This rar file is the code of the image super-resolution reconstruction network model RCAN, which can be run successfully)

本程序采用pca提取人脸特征，采用人工神经网络识别人脸。(This procedure using pca face feature extraction, using artificial neural network recognition face. )