code3

基于小波变换的图像去噪处理，通过学习小波变换的方法实现对图像的去噪处理，达到所预期的效果(Image denoising based on wavelet transform, realize image denoising by wavelet transform learning method, to achieve the desired effect)

水印代码 水印代码 水印代码 水印代码 (watermark code watermarking code watermarking code watermarking code watermarking code)

用于粒子图像测速技术的图像处理，分析得到流场信息(Image Processing for Particle Image Velocimetry and Flow Field Information Analysis)

isar成像处理，对测试数据进行处理的模板，可以显示二维像(ISAR imaging processing, the test data processing template, you can display the 2D image )

实现图像的超分辨率算法，采用最大后验（MAP）算法，实现效果不错。(Image super-resolution algorithm using maximum a posteriori (MAP) algorithm, to achieve good results.)

实现多种方法的全色和多光谱图像融合：（1）IHS变换（2）高通滤波（3）GIHS方法（4）小波变换（5）PCA （6）Brovey变换(A variety of methods of panchromatic and multispectral image fusion: (1) IHS transform (2) high-pass filter (3) GIHS method (4) wavelet transform (5) PCA (6) Brovey transform)

说明：  在autocad2007环境中直接使用API就可以亮显实体的一个示例演示(This program demonstrates how to use ObjectARX API functions to highlight and unhighlight subentities of complex entities such as ACIS solids.)

TV正则化去卷积the Iteratively Reweighted Norm algorithm for solving the generalized TV functional, which includes the L2-TV and and L1-TV problems(An Iteratively Reweighted Norm Algorithm for Minimization of Total Variation Functionals)

水表图像识别 图像预处理 哈哈就不懂四周(Water Meter Image Recognition)

图像检测的算法，Faster R-CNN算法，先对整张图像进行卷积计算，然后通过感兴趣区域池化层(RoI Pooling Layer)将选择性搜索算法推荐出来的候选区域和卷积网络计算出的特征映射图进行融合，得到候选区域对应的特征矢量，这种共享卷积计算的操作极大地减少了卷积计算的次数。而且这些特征矢量的维度统一，方便后续的分类工作。通过感兴趣区域池化层处理卷积特征，并将得到的特征送往两个并行计算任务进行训练，分类和定位回归。通过这些方法和改进的框架，Fast R-CNN 用更短的训练和测试时长，取得了比 R-CNN 更好的效果(Faster R-CNN algorithm first convolutes the whole image, then fuses the candidate regions recommended by the selective search algorithm and the feature mapping maps calculated by the convolution network through the RoI Pooling Layer to get the corresponding feature vectors of the candidate regions, which greatly reduces the number of convolution calculations. Moreover, the dimension of these feature vectors is unified, which facilitates the subsequent classification work. The convolution feature is processed by the pooling layer of the region of interest, and the obtained feature is sent to two parallel computing tasks for training, classification and positioning regression. Through these methods and improved framework, Fast R-CNN uses shorter training and testing time and achieves better results than R-CNN.)