PAPER11

利用卷积神经网络进行特征提取，并将卷积特征可视化(Feature extraction using convolutional neural networks and visualization of convolution features)

用来计算水印算法中的psnr值，非常好用一直在用这个(Watermarking algorithm used to calculate the value of psnr, very easy to use )

最小二乘法拟合圆vc实现，最小二乘法(least squares analysis)是一种 数学 优化 技术，它通过 最小化 误差 的平方和找到一组数据的最佳 函数 匹配。 最小二乘法是用最简的方法求得一些绝对不可知的真值，而令误差平方之和为最小。(least squares fitting round vc realized, least-squares method (least squares analysis) is a mathematical optimization techniques, It error by minimizing the square and a group of data to find the best matching function. Least-squares method is the most simple method to derive absolutely true value unknown, and so the sum of squared errors to the minimum.)

一段车牌分割的matlab程序 可以实现车牌的定位分割, 希望大家讨论(a division of Matlab registration procedures can be achieved by positioning plates segmentation, we hope that the discussion)

一种基于半监督的svm的图像分类方法。该方法通过聚类核的方法利用无标记样本局部正则化训练核的表达式。这种方法通过图像直接学习一个自适应的核。该程序仿真的是文章：Semi-supervised Remote Sensing Image Classification with Cluster Kernels。大家可以参考下。(A semi-supervised SVM is presented for the classification of remote sensing images. The method exploits the wealth of unlabeled samples for regularizing the training kernel representation locally by means of cluster kernels. The method learns a suitable kernel directly from the image, and thus avoids assuming a priori signal relations by using a predefined kernel structure. Good results are obtained in image classification examples when few labeled samples are available. The method scales almost linearly with the number of unlabeled samples and provides out-of-sample predictionsds)

实现了KFCM算法，对模糊图像进行聚类分析，效果良好(The KFCM algorithm is implemented)

使用GDAL库，用于遥感影像的特征点提取(Using the GDAL library, used for remote sensing image feature point extraction)

图像分割的一个小程序。经过检验，直接运行没问题。希望对大家有用，在这里分享了。(A small program for image segmentation. Tested directly run no problem. We want to share here.)

说明：  使用opencv语言绘制所有轮廓后根据轮廓长度丢弃小轮廓(Opencv draw all contours of the language used under the contour length of the drop after the small contour)

AVIRIS 高光谱遥感数据,220个波段，145*145(AVIRIS Hyperspectral data,220bands，145*145)