paper2

说明：  基于contourlet的图像融合利用的融合策略是取像素绝对值最大。此方法用得较少，有学习价值(Contourlet based image fusion using the fusion strategy is to take the absolute value of the maximum pixel. This method is used less, the value of learning)

我的毕业设计，用matlab编的关键帧提取的代码，参考了光流法的代码。是基于帧差的欧式距离，均值，方差，差异系数下的关键帧提取。代码调试通过，运行结果理想，与大家分享下。(I graduated from design, matlab key frame extraction for the code, with reference to code optical flow method. Frame difference is based on the Euclidean distance, the mean, variance, difference coefficient under the key frame extraction. Debugging through the code, run the results are satisfactory, the next to share with you.)

说明：  CUDA图像处理的程序，这个程序速度快，效率高(CUDA image processing program)

曲面拟合法是一种高精度、计算量小、抗噪性能强的方法，当前已被广泛地应用于 各种场景。比如岩石材料的变形测量、电子器件变形的测量、基于掌纹图像相关匹 配的重复定位技术等。曲面拟合法能够成功计算出亚像素位移的前提是整像素搜索阶 段可以正确搜索出模板的整像素匹配点，一旦整像素匹配点搜索出现错误，那么亚像素 测量阶段所得到的位移距离就会失去意义。 使用不同的拟合函数对相关系数矩阵进行曲面拟合，会对结果产生一定的影响，比 较常用的拟合函数有二次函数、三次函数、高斯函数等。(Surface fitting method is a high-precision, computational complexity is small, strong anti-noise performance method, has been widely used in various scenes. For example, deformation measurement of rock materials, deformation measurement of electronic devices, and repetitive location technology based on palmprint image correlation matching. Surface fitting method can successfully calculate the sub-pixel displacement on the premise that the whole pixel search stage can correctly search the template of the whole pixel matching point, once the whole pixel matching point search error, then the sub-pixel measurement phase of the displacement distance will be meaningless. Using different fitting functions to fit the surface of the correlation coefficient matrix will have a certain impact on the results. The commonly used fitting functions are quadratic function, cubic function, Gaussian function and so on.)

说明：  CA-CFAR的仿真程序，对初学者十分友好。(The simulation program of CA-CFAR is very friendly to beginners.)

对两幅图像进行相似度计算，基于相似度计算进行模板匹配，带有测试图像，可以直接运行(Calculate the similarity of the two images, the similarity calculation based on template matching, with a test image, you can directly run)

说明：  VC++.NET车牌识别、字符分割与归一化处理，图像对象BMP格式，程序将读取车牌的图像信息，归一化图像大小，动态分配存储图片的像素信息的二维数组，找到图像各列，从左列开始,垂直扫描，实施图片局部分割等，有兴趣编写车牌号识别的可参考对比下。(VC ++. NET license plate recognition, character segmentation and normalization processing, image object BMP format, the program will read the license plate image information, normalize the image size, dynamically allocate a two-dimensional array of pixel information to store the picture, and find the image columns , Starting from the left column, vertical scanning, partial image segmentation, etc. If you are interested in writing the license plate number recognition, please refer to the comparison.)

本文件中代码使用前馈卷积神经网络对图像进行去噪(In this paper, we use the feedforward convolution neural network to denoise the image.)

该代码是对图像进行二值化处理，进行图像分割(The code is to binarize the image, the image segmentation)

说明：  RGB-IHS变换：图像进行 RGB-HIS 正变换，分别对明度、饱和度、色调进行线性 拉伸显示；然后再进行反变换 (RGB-IHS transformation: the image is RGB-HIS transformation, respectively, lightness, saturation, hue, a linear stretch display then the inverse transform)