BSCB

说明：  实现了双线性插值、三次样条插值、B样条插值和最大阶次优化差值等传统多项式图像插值办法(Traditional polynomial image interpolation methods such as bilinear interpolation, cubic spline interpolation, B spline interpolation and maximum order optimization difference are realized.)

基于离散小波变换和IHS变换的遥感图像融合代码，主要用于多光谱和全色图像的融合(matlab code for remote sensing image fusion based on DWT and IHS, mainly for mutilspectral and panchromatic image fusion)

利用多线程技术把数据处理模块和图像显示模块分离，实现视频监控功能。(The use of multi-threading technology to data processing and image display module separation module for video monitoring.)

利用V4L2协议进行图像处理的编程框架结构(The utilization the V4L2 protocol for image processing programming framework structure)

易语言仿彗星真彩PNG按钮源码，易语言写的图形图象编程，很好的参考。(Easy language imitation comet true color PNG button, easy graphics programming language to write, a good reference.)

kinect采集到的深度图像中的黑洞进行像素、平均像素滤波修复(Black holes in depth images captured by Kinect are repaired by filtering pixels and average pixels)

说明：  一些相位迭代算法，还挺有用的，可以直接拿过来使用(iterative phase retrieval algorithms)

实现简单图像处理，包括256色转灰度图、Hough变换、Walsh变换、中值滤波、二值化变换、亮度增减、傅立叶变换、反色、取对数、取指数、图像平移、图像旋转、图像细化、图像缩放、图像镜像、均值滤波、对比度拉伸、拉普拉斯锐化（边缘检测）、方块编码、梯度锐化、灰度均衡、直方图均衡、离散余弦变换、维纳滤波处理、逆滤波处理、阈值变换、高斯平滑。(simple image processing, including color to grayscale 256, the Hough transform, Walsh transform, Median filtering, binary conversion, brightness changes, Fourier transform, and color-from the few to admit index, image shifting, image rotation, refined images, image scaling, image mirroring, mean filtering, contrast stretching, Laplacian sharpening (edge detection), block codes, Sharpening gradient, gray balance, histogram equalization, discrete cosine transform, Wiener filter, reverse filtering, threshold transform, Gaussian smoothing.)

Mean shift algorithm for segmentation and smoothing images. the example images are horses.

一种基于半监督的svm的图像分类方法。该方法通过聚类核的方法利用无标记样本局部正则化训练核的表达式。这种方法通过图像直接学习一个自适应的核。该程序仿真的是文章：Semi-supervised Remote Sensing Image Classification with Cluster Kernels。大家可以参考下。(A semi-supervised SVM is presented for the classification of remote sensing images. The method exploits the wealth of unlabeled samples for regularizing the training kernel representation locally by means of cluster kernels. The method learns a suitable kernel directly from the image, and thus avoids assuming a priori signal relations by using a predefined kernel structure. Good results are obtained in image classification examples when few labeled samples are available. The method scales almost linearly with the number of unlabeled samples and provides out-of-sample predictionsds)