otsu

rk3399硬件编解码demo及文档

sample illust back image2 mask sample

说明：  matlab下的相机标定工具箱，包含角点检测，求取相机内参，误差分析，求相机外参，图像校正等多种功能。附带有实验用的20张图像。(matlab under the camera calibration toolbox, including corner detection, strike the camera restricted reference materials, error analysis, seeking the camera outside the parameters, image correction, multiple functions. Comes with the 20 experimental images.)

把分裂Bregman方法运用到图像处理中，发现这种方法比以前去模糊方法要好很多。(To split Bregman method applied to image processing, and found that this method defuzzification method is much better than before.)

图像处理标准测试图片库，用于数字图像处理各种仿真实验。(Standard test image gallery image processing to digital image processing all kinds of simulation experiments. )

说明：  小波分析增强滤波。小波变换的原理类似傅里叶变换，只是把三角函数基换成了小波基。与傅里叶变换不同，小波变换有两个变量：scale和translation。scale控制小波函数的收缩，其导数即为频率，translation控制小标函数的平移，平移量对应时间。通过信号的伸缩平移，可以得到某种重合情况，这样积分也会得到一个极大值，不同的是，得到频率成分的同时，还可以知道该频率的时间位置。(Wavelet analysis enhances filtering.The wavelet transform works like the Fourier transform, except that the trigonometric basis is replaced by a wavelet basis. Unlike the Fourier transform, the wavelet transform has two variables: scale and Translation. Scale controls the contraction of the wavelet function, its derivative is frequency, translation controls the translation of the small scale function, and the translation corresponds to the time. By stretching and shifting the signal, you can get some kind of coincidence, so that the integral will also get a maximum, but the difference is that when you get the frequency component, you can also know the time position of that frequency.)

针对可见光与红外图像的特点和难点，提出了可见光与红外图像配准与融合中的关键技术，即: 使用新型的基于一维最大类间方差和最大连通性测量的图像分割方法对源图像进行分割来更好地实行图像粗 配准 使用新型的特征点提取方法，特征点的匹配及误匹配的消除来更好地实行图像精配准 采用新型的基 于区域的树状小波活性测度计算来实现树状小波图像融合 利用自生成神经网络来实现模栩图像融合. (For visible light and infrared images of the characteristics and difficulties, a visual and infrared image registration and integration of key technologies, namely: the use of new one-dimensional based on the largest variance between-class connectivity and the largest measuring method of image segmentation source image segmentation to better implementation of coarse image registration the use of a new type of feature point extraction method, feature points of the match and the elimination of false matches to better the implementation of image fine registration the use of new tree-based wavelet calculated to measure the achievement of the activity tree wavelet image fusion the use of self-generating neural network to achieve image fusion Xu mode.)

自动种子区域生长代码，用MATLAB运行，不必选择种子点 可以自动选择阈值 实现图像分割！(The automatic seed region growing code, run, do not have to select seed point can automatically select the threshold image segmentation using MATLAB)

说明：  改进拉普拉斯能量和的尖锐频率局部化 Contourlet 域多聚焦图像融合方法(Sum-modified-Laplacian-based Multifocus Image Fusion Method in Cycle Spinning Sharp Frequency Localized Contourlet Transform Domain)

说明：  利用vc画图，特点是可以画一些有特殊效果的几何图像(use vc drawing, painting features can be some special effects of geometric images)