dft_watermarking

SDK_key: 人脸追踪(FT) Key 5qTrdeA43zdBXJZt7HM1x1wX9XGt7QicRU6Nt8rXLQAn 人脸检测(FD) Key 5qTrdeA43zdBXJZt7HM1x1weJvY2koYyzGARH6wVoTVw 人脸识别(FR) Key 5qTrdeA43zdBXJZt7HM1x1wmUKoEpvhgJYHd5xAsFig3 年龄识别(Age) Key 5qTrdeA43zdBXJZt7HM1x1xPHL78Ekcog6LU5iNCCNLj 性别识别(Gender) Key 5qTrdeA43zdBXJZt7HM1x1xWSjNHHcbTHHP9VuHLX1rf 此处APP_Id与SDK_Key仅适用于ArcFace v1.1， 不适用于其他版本。(DK_key: Face Tracking (FT) Key 5qTrdeA43zdBXJZt7HM1x1wX9XGt7QicRU6Nt8rXLQAn Face Detection (FD) Key 5qTrdeA43zdBXJZt7HM1x1weJvY2koYzGARH6wVoTVw Face Recognition (FR) Key 5qTrdeA43zdBXJZt7HM1x1wmUKoEpvhg JYHd5xAsFig3 Age Identification (Age) Key 5qTrde A43zdBXJZt7HM1x1xPHL78Ekcog 6LU5iNCCNLj Gender Key 5qTrdeA43zdBXJZt7HM1x1xWSjNHcbTHHP9VuHLX1rf Here APP_Id and SDK_Key are only applicable to ArcFace v1.1, not to other versions.)

在linux环境下，实用c++编写的有关实用mean shift进行视频跟踪，视频分割的很好的程序，运行良好……(Practical mean shift in the linux environment, practical C++ written in the video track, video segmentation procedures, good running ...)

[1] 鼠标拖动裁剪框可移动裁剪区域的位置 联合开发网 - pudn.com

用小波变换进行图像增强，先对原始图像进行非下采样的小波分解，在对每一层的高频分解系数进行处理，得到变换后的小波系数，再进行小波重构。(Image enhancement using wavelet transform, the original image and non-sampling wavelet decomposition in the high frequency decomposition coefficients of each layer, get the wavelet coefficients after the transformation, then the wavelet reconstruction. )

说明：  二值化算法，含otsu,niblack,kapur,kittlerMet等方法(Binarization algorithm, including otsu, niblack, kapur, kittlerMet and other methods)

实现图像文件（如bmp等）的读取、显示、真彩图转换成灰度图、灰度图转化为二值图及绘制图像直方图功能。(Achieve an image file (such as bmp, etc.) to read, display, true color conversion to grayscale, converted to grayscale and binary image histogram function to draw the image.)

此代码是小波零树算法的matlab实现程序，子程序较为齐全，包括最后计算压缩图像的峰值信噪比和压缩效果的源码。(This code is the wavelet zero-tree algorithm matlab implementation procedures, subroutines are more complete, including the final calculation of the peak signal to noise ratio and the compressed image compression source.)

说明：  织物疵点检测，有GUI界面，可自动识别疵点并分类(Fabric defect detection, GUI interface, automatic defect identification and classification)

转：https://blog.csdn.net/jinshengtao/article/details/26278725 混合高斯背景建模是基于像素样本统计信息的背景表示方法，利用像素在较长时间内大量样本值的概率密度等统计信息(如模式数量、每个模式的均值和标准差)表示背景，然后使用统计差分(如3σ原则)进行目标像素判断，可以对复杂动态背景进行建模，计算量较大。 在混合高斯背景模型中，认为像素之间的颜色信息互不相关，对各像素点的处理都是相互独立的。对于视频图像中的每一个像素点，其值在序列图像中的变化可看作是不断产生像素值的随机过程，即用高斯分布来描述每个像素点的颜色呈现规律单模态(单峰)，多模态(多峰)(Gaussian mixture background modeling is a background representation method based on the statistical information of pixel samples. Statistical information such as the number of patterns, the mean and standard deviation of each pattern are used to represent the background. Statistical difference (such as 3_principle) is used to judge the target pixel. Complex dynamic background modeling has a large amount of computation. In the Gaussian mixture background model, it is considered that the color information between pixels is uncorrelated and the processing of each pixel is independent of each other. For each pixel in a video image, the change of its value in a sequential image can be seen as a random process that produces pixel values continuously, i.e. Gaussian distribution is used to describe the regularity of color rendering of each pixel in single mode (single peak) and multi-mode (multi-peak).)

在高斯混合噪声背景下实现SLIM谱估计算法和l1范数SLIM谱估计法，并在-5到15的信噪比条件与CRLB对比均方频率误差(the paper achieves the SLIM spectral estimation algorithm and l1-SLIM spectral estimation method under the Gaussian mixture background noise,then compares the mean square frequency error with CRLB under SNR from-5 to 15 )