p300

说明：  lsb数字水印算法，SB算法利用了数字图像处理中位平面的原理,即改变图像的最低位的信息,对图像信息产生的影响非常小,人眼的视觉感知系统往往不能察觉。以一幅256灰度的图像为例, 256 灰度共需要8 个位来表示,但其中每一个位的作用是不一样的,越高位对图像的影响越大,反之越低的位影响越小,甚至不能感知。(Digital watermarking algorithm based on lsb)

说明：  图像匹配相关文献7篇，主要有小波变换用于理论研究及匹配的算法实现。对于刚进行图像匹配研究的人员很有帮助(Matching literature 7, mainly used for theoretical research on wavelet transform and matching algorithm. Matching of the images for just the staff very helpful)

使用分裂Bregman算法做图像去噪，收敛速度很快，保持缘特征(using Splitting Bregman algorithm do image denoising, fast convergence to maintain edge features)

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.)

实现图像小波分解，可以自行指定分解级数，采用daubenchies小波(Achieve the wavelet decomposition, you can specify the decomposition of their own series, using wavelet daubenchies)

说明：  运用小波变换将图像从空间域转换到频率域，自己写的代码，欢迎讨论学习(Using wavelet transform to transform image from spatial domain to frequency domain)

vtk mfc 显示DICOM影响，自己编的，还可以的，网上相关资料较少(no32456789808976543324567890-0987564433)

本解码器类支持普通jpeg文件格式，这也是目前大多数jpeg文件所采用的格式，此格式主要特点是数据精度为8位，采用Huffman编码的普通DCT帧（不支持扩展串行和递进模式及数学编码）。本解码器类的 IDCT算法采用三种模式，分别是浮点解码、定点整数解码和定点整数MMX优化解码，您可根据具体情况选择。(The decoder class support common JPEG file format, which is currently the most JPEG files in the format and the main characteristics of this format is data for 8-bit precision, using Huffman coding DCT common frame (does not support extended serial and progressive model and arithmetic coding). The decoder of the IDCT algorithm uses three modes, respectively, floating-point decoding, fixed-point integer decoding and fixed-point integer MMX optimization, you can choose according to the specific circumstances.)

实现一个简单的PCA降维与重构程序，用到的数据在.txt文件中。还有用于测试的.m文件(To achieve a simple PCA dimension reduction and reconstruction procedures)

说明：  基于人体手指静脉图像分割算法的研究(Research on segmentation algorithm of human finger vein image)(Research on segmentation algorithm of human finger vein image)