WPF学习- 不规则窗体 实例源码下载

本程序对同一图像增加噪声后，进行均值滤波、高斯平滑滤波和中值滤波三种方法的去噪和结果比较， 并进行了评价指标PSNR和SSIM的计算以及算法耗时的统计。 ( The program on the same image after the noise increases, mean filter, de-noising and results of the Gaussian smoothing filter and median filter three methods of comparison, and the index PSNR and SSIM calculation algorithm and time-consuming statistics.)

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.)

通过使用块匹配法实现运动矢量的检测，块大小和搜索区域大小可自定(Achieved through the use of block matching motion vector detection, block size and search area size can be customized)

说明：  Perona和Malik在热传导方程的基础上，建立了各向异性扩散方程并将其应用到了图像处理中尺度空间的图像平滑上，该模型针对图像的边缘部分和非边缘部分进行不同性质的图像处理，同时解算方程的迭代格式简单，克服传统滤波的主要缺陷，是图像质量大为改善，为图像的边缘检测和增强开辟了新的方向。(This process smoothes regions while preserving, and enhancing, the contrast at sharp intensity gradients.)

Jsteg隐写算法[23][24]由D. Upham提出，该算法将秘密信息嵌入在量化后的DCT系数的LSB上，但值为-1、0、+1的DCT系数例外。提取秘密信息时，也只是将隐藏信息的图像中不等于-1、0、+1的量化DCT系数的LSB取出即可(steganography of jsteg)

非局部平均，用来去除灰度图里面的噪声，效果明显(Probability Non-Local Means)

说明：  自己编写的基于直方图均衡化以及边缘增强的程序！(I have written based on histogram equalization and edge enhancement procedure!)

读取bmp格式的图片，并且能对其进行相关的图像处理，具体的图像处理有平滑，锐化等等，是关于遥感图像处理。(Bmp format to read the picture, and can be related to image processing, image processing has specific smoothing, sharpening and so on, are on the remote sensing image processing.)

c# 窗体动画特效(渐变)

SIFT特征提取演算法(包含匹配以及除错机制RANSAC)-可用于两张影像之特征点匹配 (SIFT feature extraction algorithm (including the match, as well as debug mechanisms RANSAC)- can be used for two images of the feature points matching)