Convolution_model

卷积神经网络深度学习，可以识别多种图像，并自动解出所需要的结果(Deep learning of convolutional neural networks)

数字图像处理中对分类器优劣的判定常用的ROC/ACU源码。希望对你有用。(The ROC/ACU source code commonly used in the determination of the quality of the classifier in digital image processing. I hope useful to you.)

分别用kmeans、fcm、kfcm实现图像分割(use kmeans, fcm and kfcm segment image)

c++实现的sift，可以分步观看实现效果(c++ implementation of the sift, you can watch step by step to achieve results)

matlab电子稳像块匹配算法程序代码 图片路径请自行更改(Electronic Image Stabilization matlab code image block matching algorithm to change the path at your own)

基于bp神经网络的车牌字符识别源程序，采用字符比对的方式进行切割(The structures of the neural networks were designed using a constructive algorithm where the basic idea was to start with a small network,then add hidden units and weights incrementally until a satisfactory solution be found .The higher efficiencies were for a 30×17×10 number network and letter network)

说明：  vibe算法实现，该算法是2011年提出，具有运行占用空间小的特性(Vibe algorithm, which was proposed in 2011, has the characteristics of small running space)

Shap Context based Shape recognition

说明：  实现机器视觉双目标定，三维重建等算法，具有很好地擦考价值( Robot with two cameras to switch recognition system. (Note that not binocular vision) and the reference used opencv1.0 cmv. )

数字图像处理技术 边缘检测 Canny sobelC# 数字图像处理技术 边缘检测 Canny sobelC#(Digital image processing technology edge detection Canny sobelC# digital image processing technology edge detection Canny sobelC#)