cx

graphcut的最新改进，在网格上应用graphcut，作者将其称为gridCut,此压缩包内含文章与源代码，出自CVPR2012,关注计算机视觉的同学可以详细参考，代码已调试通过(the new advance of graphcut, named gridCut, derived from CVPR 2012, useful to guys on ComputerVision.The code is runnable.)

在目标图像中找出已经给出的训练图像。通过训练训练图像得到参数，来找出目标图像中的训练图像(Has been given in the target image to identify the training image. TRAINING image parameters to identify the training images of the target image)

根据RBM深度网络（Hinton，2006）进行MINST手写文字的分类器的训练，利用训练得到的权值制作了这个小程序，通过这个程序可以看出训练结果对数据集内的测试样本和训练样本都能进行很好的识别，但是对其他的手写字体识别就没有那么好了。(According to RBM depth network (Hinton, 2006) conducted MINST handwritten text classifier training, using the training to get the right value to produce this small program, this program can be seen through the results of the training data set and the training sample test samples are can be well identified, but on the other handwriting recognition is not so good.)

说明：  批处理一批图片，实现对其中的图像提取几何特征参数。(Batch number of pictures, images of which the realization of the geometric characteristic parameter extraction.)

说明：  分类，纹理特征，提取特征向量，matlab 7.0 原程序，classifer,texture(Classification, texture features, feature vector extraction, matlab 7.0 original procedure, classifer, texture)

使用光流法对动态图像进行彩色图像的显示，原文件要求用64位系统，32位系统的混合编译已经做好了(Optical flow method using dynamic image display color images, the original file system requires a 64-bit, 32-bit compiler mixing system has already done)

说明：  可用于图像分割、识别分类、语音识别等的代码实现(Recognition classification)

对火焰惊醒提取轮廓 并求取周长面积 圆形度(Woke up on the flame contour extraction and the degree to strike a circular perimeter area)

视觉注意力模型，寻找感兴趣区域，模仿人眼找出最感兴趣的区域，再找出第二感兴趣的区域，以此类推(Visual attention model to find the region of interest, to imitate the human eye to identify the most interesting region, and then find the second region of interest, and so on)

该工具箱可实现matlab编程和zemax通信，同时借助于matlab 强大的编程能力以及zemax的光学设计能力，为光学领域工作的科研人员提供了新的途径。(This program can realize the communication between the matlab and zemax, very helpful for optical engineer and student whose major in optical science.)