Image Feature Extraction of Code

高光谱图像进行MNF变换，采用MAF评价图像的噪声；处理过程与ENVI软件中的完全一样。(MNF transformation of hyperspectral images, using noise MAF to evaluate the image.the process is exactly the same with ENVI software .)

随着视频的播放进行眼球追踪，如果眼镜反光会影响正确率(eyeball tracking in video p.s. note that the reflection of glasses may influence the performance)

一个简单的虚线类，绘制各种虚线的C++类库，请看效果截图，可绘制出各种彩色的虚线效果。画横向或竖向虚线，以及对角线的虚线框效果，都是可以的，带有一个演示程序。(A simple dashed class, draw various dashed C++ library, see the effects shots, you can draw a variety of color dotted effect. Draw horizontal or vertical dashed line, as well as the effect of diagonal dashed box, are possible with a demo program.)

在最不重要位替换嵌入算法的基础上引入矩阵编码，增强水印隐蔽性，有效地提高水印嵌入效率。(On the basis of the least significant bit embedded algorithm is introduced to Replace the matrix coding, to enhance hidden watermark, the watermark embedding effectively improve efficiency.)

一种精确地二维图像配准方法，实现亚像素的配准。(An accurate two-dimensional image registration method to achieve sub-pixel registration.)

说明：  matlab实现基于稀疏表示的高光谱图像分类(Hyperspectral image classification based on sparse representation using MATLAB)

MD5 algorithm can be directly called debugging no problem not subject to environmental restrictions

运用matlab提取视频，显示出视频图像的图像特征，并以柱状图形式显示(Use matlab extract video shows the image feature of the video image, and is displayed in histogram form)

　　本函数选用阈值分割的方法来完成瞳孔定位。根据图像的灰度分布特性，瞳孔部分的灰度值最小，其次为虹膜部分，最大的为巩膜部分。因此在灰度直方图中，第一个大峰值的邻域即是瞳孔所在区域。(Function selects the threshold segmentation method to accomplish the pupil location. Based on image gray distribution features, the pupil part of the grey value of the minimum, followed by the iris part, the biggest part of sclera. So in gray level histogram, the peak value of the first big neighborhood is the pupil area.)

BP神经网络图像分类程序,代码很好懂，适合初学者。样本选的不是很大。(BP neural network image classification procedures, code easy to understand for beginners. Sample selected is not great.)