jbigkit-2.1

说明：  对于X光骨骼增强，利用拉普拉斯变换，灰度变换，高频滤波对其增强(For X-ray bone enhancement, Laplace transform, gray transform and high frequency filter are used to enhance it)

对全息图进行卷积法的再现，利用matlab计算全息图模拟仿真(Reappearance of convolution method for hologram)

模糊C均值分类，用于图像处理中 很好用的，极力推荐 (Fuzzy C-means classification, used for image processing in a very good use, and strongly recommend)

对一维信号，用正交重叠变换做DCT和逆DCT(Of one-dimensional signals, using orthogonal lapped transform DCT and inverse DCT to do)

shearlet变换，能够实现图像融合的代码，里面有例子和说明(Shearlet transform, to achieve image fusion code, which has examples and instructions)

Harr特征的几种在matlab环境下的实现(Implementation of several Harr features in Matlab environment)

两个圆形相互碰撞(two round collision)

说明：  UNet最早发表在2015的MICCAI上，短短3年，引用量目前已经达到了4070，足以见得其影响力。而后成为大多做医疗影像语义分割任务的baseline，也启发了大量研究者去思考U型语义分割网络。而如今在自然影像理解方面，也有越来越多的语义分割和目标检测SOTA模型开始关注和使用U型结构，比如语义分割Discriminative Feature Network(DFN)(CVPR2018)，目标检测Feature Pyramid Networks for Object Detection(FPN)(CVPR 2017)等。(Its influence has reached 70% in 2015. Then it became the baseline that most of the medical image semantic segmentation tasks, and inspired a large number of researchers to think about the U-shaped semantic segmentation network. In the aspect of natural image understanding, more and more SOTA models of semantic segmentation and object detection begin to pay attention to and use U-shaped structure, such as semantic segmentation, discriminative feature network (DFN) (cvpr2018), feature pyramid networks for object detection (FPN) (CVPR 2017), etc.)

说明：  以稀疏基有离散余弦变换基（DCT）和快速傅立叶变换基（FFT）做为稀疏基，高斯随机矩阵、部分哈达玛矩阵为测量矩阵，L1范数、正交匹配追踪算法（OMP）为重建算法进行压缩感知算法实现。 以f = cos(2*pi/256*t) + sin(2*pi/128*t)做为原信号，取原信号f的20%做为输入进行压缩感知重建。(The sparse basis includes discrete cosine transform (DCT) and fast Fourier transform (FFT) as sparse basis, Gaussian random matrix and partial Hadamard matrix as measurement matrix, L1 norm and orthogonal matching pursuit algorithm (OMP) as reconstruction algorithm. In this paper, the reconstructed signal is reconstructed by using the original sensing signal (sinf * t) as the original input signal (i.e. sinf * t * 2) + 2 * s * t * as the input signal.)

能够得到二维、三维voronoi图，修改后可以获得任意数量的voronoi图。(The two or thress-dimensional Voronoi diagram can be obtained, and any number of Voronoi diagrams can be obtained after modification.)