image_mva

用于虹膜定位……定位外圆之前需要进行边界跟踪，此程序实现此功能(For Iris Location ... Location ... before the need for outer border tracking, this procedure realize this feature)

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.)

3d 重建 包括特征点的提取，匹配，以及三维点云的建立(3d reconstruction ,including feature detection and 3 D points cloud ,the change from 2D to 3D)

使用canny边缘检测算法，提取图像轮廓(Canny edge detection algorithm is used to extract image contour.)

几种经典的图像平滑去噪算法程序，其中包括小波软阈值和硬阈值处理。还附送三个图像质量评价程序(several classic image denoising smoothing algorithm procedures, which include thresholding wavelet soft and hard threshold processing. Also attached three image quality evaluation procedures)

研究生机器视觉课程的大作业 运动目标检测 (moving target detect)

采取逆滤波和维纳滤波两种图像恢复算法对退化图像的恢复实现过程。 (taken inverse filter and two Wiener filtering algorithm to image restoration of degraded images to achieve the restoration process.)

线性插值射线追踪法，设置模型为一三层模型，范围100m×100m(Linear interpolation ray tracing method, set the model for a three-tier model, the range 100m100m)

源码包括了常用的图像处理方法，代码详细，适合初学者(Source code, including the commonly used image processing method, the code in detail, suitable for beginners)

令x(n)=5exp(j*0.15*n*n)+6exp(j*300n-j*0.15*n*n) ，w(n)为高斯窗函数。试用matlab软件，取不同长度的窗函数，分别求x(n)离散短时傅里叶变换，并进行信号重构。(ORDER x (n) = 5exp (j* 0.15* n* n)+6exp (j* 300n-j* 0.15* n* n), w (n) for the Gaussian window function. Trial Matlab software, take different lengths of the window function x (n), respectively, seek to discrete short-time Fourier transform, and to reconstruct the signal.)