fourier

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.)

一种基于non-sample的纹理合成demo，程序性能还有待优化，效果还不错.(texture synthesis demo.)

卷积神经网络（Convolutional Neural Network）是一个专门针对图像识别问题设计的神经网络。它模仿人类识别图像的多层过程：瞳孔摄入像素；大脑皮层某些细胞初步处理，发现形状边缘、方向；抽象判定形状（如圆形、方形）；进一步抽象判定（如判断物体是气球）。(Convolutional neural network is a neural network specially designed for image recognition. It imitates the multi-layer process of human recognition image: pupil ingestion of pixels; some cells in the cerebral cortex preliminary processing to find shape edges and directions; Abstract judgment of shape (such as circles and squares); and further Abstract judgment (such as judging objects are balloons).)

1990年—adaptive multi-band CFAR detection of an optical pattern with unknown spectral distribution.pdf

基于MATLAB的SOM神经网络设计源程序(MATLAB-based SOM neural network design source)

说明：  通过hough变换求图像中的圆的参数（圆心坐标和半径）(Through the hough transform for image circle parameters (center coordinates and radius))

实现上位机对wifi智能车的控制，接收路由器传输图像并显示界面是用Qt4.0编写，开发环境QtCreater 图像处理Opencv(Host computer for wifi smart car control, image transmission and display the receiving router)

说明：  face recognition example for learning

IDL开发的求取两幅图像相关系数的程序，用于影像融合质量评价(IDL to strike a developed procedures for the correlation coefficient of two images for image fusion quality evaluation)

实现dicom和bmp之间的转换。适合医学图像中的最初学习。(transformation between dicom and bmp image.)