bianyuanjiance

说明：  行为识别3D卷积神经网络,ucf或者KTH数据集都可以使用(3DCNN for action recognition)

在指纹特征提取中，结合方向图和图像局部灰度方差对指纹图像进行分割，然后再进行阈值分割去处边缘效应得出较好的分割结果。(In the fingerprint feature extraction, the combination of pattern and image local variance of gray-scale fingerprint image segmentation, and then conducted threshold segmentation edge effects come to a better place for the segmentation results.)

利用matlab实现不同曝光成度的图像融合，matlab实现HDR功能(Using matlab to realize image fusion with different exposure degrees, and using MATLAB to realize HDR function)

球面坐标定位法校正鱼眼图像畸变，使用visual studio 2008 编写，需要OpenCV的支持(Spherical coordinates locating fish eye image distortion correction, prepared using visual studio 2008, requires the support of OpenCV)

品质因子可调的离散小波变换工具箱，可通过参数灵活控制小波函数的频域窗宽(Discrete wavelet transform toolbox with quality factor adjustable, flexible control parameters through the wavelet function in the frequency domain window width)

说明：  基于空域的脆弱水印算法，该方法最具代表性的是最低有效位（LSB）法，也就是文件中的方法，两个文件分别给出了水印的生成和检测。(Airspace based on fragile watermarking algorithm, the method is the most representative of the least significant bit (LSB) method, which is the method of the document, two documents were given watermark generation and testing.)

用TV算法实现图像去噪，包含TV，PM模型等(in this MTV, the diffusion is along the edge direction of the original noisy image(maybe its smoothed version using a Gaussian filter of small scale),it can preserve edge and suppress staircase very well.)

mp算法实现的图像稀疏分解表示 ，已经调试通过，供参考学习(Image fusion based on wavelet transform has been debugged, for reference study)

自己用水平集方法编的，实现了医学图像的分割，效果不错，可试一下(Their allocation by level set method, and realize the medical image segmentation, the effect good, can try)

使用OpenCV实现特征点的查找以及两幅图像中的特征点匹配(Use the function findHomography to find the transform between matched keypoints. Use the function perspectiveTransform to map the points)