dlfg

基于线性正则变换与菲涅尔变换的图形加密方法，实现广义线性正则变换的加密解密过程。(Based on linear canonical transformation and Fresnel transform graphics encryption methods, implementation of generalized linear canonical transformation encryption decryption process. )

说明：  SAR影像单视数据转为多视数据，数据间相互转化，快捷处理SAR数据(Single-look SAR image data into a more visual data, data inter-conversion, fast processing SAR data)

全参考型视频质量评价方法，基于机器学习和视频特征提取，发表与2012年TMM(FR VQA method based on machine learning and video feature )

一个非常有用的超像素算法，用于图像分割,文件夹包含文章,采用matlab和c混编(a very useful superpixels algorithm，can be used for image segmentation,the file contatins paper,the matlab and c are mixed for exeution)

基于DCT的数字视频水印源程序，Matlab编写，可以直接运行(DCT-based digital video watermarking source code, Matlab can be run directly)

为数字图像水印提供多种攻击方式，其中包括JPEG压缩、高斯低通滤波等多达十种攻击方式。(Offers a variety of attacks of digital watermarking ,including the jpeg compression, Gaussian low-pass filtering, up to ten different attacks)

说明：  基于引导滤波的图像信息分层算法，可实现高低频信息分离，分段处理功能(The image information hierarchical algorithm based on guided filtering can realize the separation of high and low frequency information and the segmentation processing function.)

说明：  LBP是一种用来描述图像局部纹理特征的算子；它具有旋转不变性和灰度不变性等显著的优点。(LBP is an operator used to describe local texture features of images; it has significant advantages such as rotation invariance and gray invariance.)

图像 自动 标注 通过分析 训练集 ，学习 图像 和标注词 之间的关系，得出 之间的关系，得出 一些规则， 然后使用这些规则 自动 推导出 图像 最适合的标注词 ，这些标注词代表了图像的 ，这些标注词代表了图像的 高层 语义信息 。(Automatic image annotation by analyzing the training set, learning image and mark the relationship between words, the relationship between the draw, draw some rules, and then use these rules to automatically derive the most suitable image annotation words, these words represent the image annotation , these words represent the image annotation level semantic information.)

图像修复的一些常用模型，与tv模型，cdd模型，bscb模型，还有基于纹理的修复方法。(Some common model image restoration, and tv model, cdd model, bscb model, as well as repair method based on texture.)