mangjuan

利用最佳直方图熵法（KSW熵法）及穷举法实现灰度图像阈值分割(The best the histogram entropy method (KSW entropy method) and the brute-force method to achieve gray image threshold segmentation)

双目匹配计算视差，生成深度图。（前提是用自己标定好的摄像头拍的图片，导入内外参数然后进行立体匹配）(Binocular matching calculates parallax and generates depth map.(The premise is to take a picture with your own calibrated camera, import internal and external parameters, and then stereo matching))

一些使用支持矢量机进行图像分割的算法，以及相关的文献资料，打包下载的好东西哦(Some use support vector machine algorithm for image segmentation, and related literature, package download a good thing)

图像处理中边缘提取几种方法的matlab代码(many edge extraction codes about image processing)

用于轴承球与滚道之间，模拟生成非高斯随机粗擦表面(Analog generate non-Gaussian random rough surfaces rub)

对图像（Bmp）的智能读入界面设计，源代码(Read image (BMP), intelligent interface design, source code)

用lbp实现纹理特征提取，并分类说明: 一共有三个m文件，一个是lbp.m, 存放主要的lbp算法， 一个是getmapping,用以做算法的辅助函数， 一个是lbptest.m,存放着测试代码。 这三个文件需要放到同一个文件夹，并在文件夹中添加相应的图片， 具体的图片名字见lbptest.m的代码，运行lbptest.m可以查看结果。代码最后给出效果图 这三个文件是最传统的LBP方法，有256种。(With lbp achieve texture feature extraction and classification Description: A total of three m files, one is lbp.m, store the main lbp algorithm, One is getmapping, helper functions for doing arithmetic, One is lbptest.m, kept the test code. These three documents need to put the same folder, and add the appropriate folder, pictures, See lbptest.m specific name of the picture of the code, run lbptest.m can view the results. Finally renderings code These three documents are the most traditional LBP method, there are 256 kinds.)

一个盲去卷积程序，可以实现去除图像的各类模糊，同时可进行相关参数的自适应调整。(A blind deconvolution process can be achieved to remove all kinds of image blur, while the relevant parameters can be adaptive.)

对采样得到的180幅断层图像进行重建，并针对其中的一幅图像进行处理，并且统计图像中颗粒的大小和数目！(Tomographic images of 180 samples obtained were rebuilt, and for which an image processing and image size and number of particles statistics!)

图像增强，包括图像的平滑、锐化、边缘识别等操作(Image enhancement, including image smoothing, sharpening, edge detection and other operations)