PSIR_ISIR_IRW

包括回归分析和概率统计，结合PCA的尺度不变特征变换(SIFT)算法，计算晶粒的生长，入门级别程序。( Including regression analysis and probability and statistics, Combined with PCA scale invariant feature transform (SIFT) algorithm, Calculation of growth, entry-level program grain.)

实现了一个二维小波分解、重构程序，对一副16*16的数字图像进行了二层小波分解和重构。(A two-dimensional wavelet decomposition and reconstruction program is implemented, and a 16*16 digital image is decomposed and reconstructed by two-level wavelet.)

jpeglib的库文件，方便实现很多关于jpeg的操作，例如格式转换等等。(jpeglib the library file to facilitate the achievement of the operation of a number of jpeg, for example, format conversion and so on.)

画图程序 画直线 矩形 圆 椭圆 可填充(draw line .rectangle .circle .roundrectangle. can be filled)

基于matlab的三维重建代码，提取两幅图片的匹配点(Based on three-dimensional reconstruction of the matlab code, extract the two images match point)

图像处理中C#畸变校正程序，针对鱼眼图像的径向畸变校正，利用空间直线在校正图像中仍然为直线的基本原理，且直线在除法模型下为圆弧，从而可以通过检测圆弧对鱼眼图像进行畸变校正。(Image processing program C# distortion correction for radial fisheye image distortion correction, the use of space in a straight line in the corrected image as the basic principle is still straight, and a straight line at the division model is a circular arc, so that the arc can be detected by fish eye image distortion correction.)

： 对一种基于图像几何重心的特征点提取算法进行了改进 改进后的算法可以提取任何边缘线上凹凸处的特征点 其基本 思想是，首先提取图像的边缘轮廓线，计算封闭边缘线和非封闭边缘线的几何重心 然后以重心为极点，对边缘点极坐标化，形成 幅角-极径曲线，在该曲线上寻找局部极大极小值点 最后根据局部非极大（小）抑制原则对极大（小）值点进行取舍获得特征点 模 拟结果表明算法计算简单 稳定性好 该方法提取的特征点能准确地反映目标的形状，对目标的识别 跟踪以及三维表面重建等都 具有重要的价值(This paper modifiesakindoffeatureextractingalgorithmbasedonimageedge.First， imageedgeoutlineisextracted. Second， geometricgravitycenterofedgeoutlineiscalculated.Third， argument-polarradiuscurveofpolarcoordinatesystemwhose poleisgeometricgravityisformed， andmaximumandminimumvaluepointsaresearched.Atlast， featurepointsareobtainedby selectingmaximum （minimum） valuepointsaccordingtolocalnon-maximum （minimum） depressionprinciple.Theresultindicates thatthealgorithmissimpleanditsstabilityisgood.Itisimportantforobjectrecognitionandthree-dimensionreconstruction.)

读取jpeg图片数据并输出到txt文本中，再从txt文本中读取数据生成图片(Reading image data and outputs to txt, and then read the data generated image txt text)

基于OpenCV的hough变换检测图像直线,本代码能够识别焊缝跟踪功能。(OpenCV based hough transform to detect linear image, the code can identify seam tracking.)

利用盲卷积图像复原方法，对模糊图像进行图像复原，可以达到比较好的效果。(Blind deconvolution image restoration)