LayerDrawable

　　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.)

Matlab环境下的几个数字图像处理实验，包含图像灰度变换、直方图均衡化、直方图匹配、邻域平均、局域增强、中值滤波、图像的锐化等(Several digital image processing experiments, including gray transform, histogram equalization, histogram matching, neighborhood average, local increase, median filtering and image sharpening, etc.)

广义高斯概率分布函数的指数估计，包括矩估计和最大似然估计，并对这两种估计进行了比较(exponential cosfficients estimation for generalized Gaussian pdf，include moment estimator and Maximum Likehood estimator. )

说明：  图像特征提取的Contourlet变换工具包，可以设置分解层次，例如，三层分解提取17维特征，用于纹理图像或者SAR图像分割应用中(Image feature extraction toolbox of Contourlet transform, you can set the level of decomposition, for example, three level with 17-dimensional, for the segmentation on texture image or SAR Image)

LPQ——TOP特征提取源码及其应用，能够很好提取动态的表情特征，可以用在表情识别以及姿态检测上。(LPQ- TOP feature extraction and its application source code, can be a good dynamic expression feature extraction, can be used on face recognition and gesture detection.)

一种快速图像阈值分割法，不是otsu或迭代法，Wellner 1993快速自适应的图像二值化方法，有具体使用方法，很详细(A fast image thresholding segmentation method, not otsu or iterative methods, Wellner 1993 fast adaptive image binarization method)

完成声音信号的分帧，加窗，PLCC特征提取等功能(Complete voice framing, windowing,PLCC detection and other functions)

说明：  图像增强算法，包括灰度线性变换、灰度非线性变换、直方图均衡化，掌握基于MATLAB的各个算法的图像增强的实现。(Image enhancement algorithms, including gray linear transformation, gray non-linear transformation, histogram equalization, master the realization of image enhancement based on MATLAB.)

说明：  使用gpu、cpu并行进行sift算子计算匹配，能够在原来的基础上加速处理，但对显卡要求较高，具体环境配置使用方法可以参照mannual(SiftGPU is an implementation of SIFT [1] for GPU. SiftGPU processes pixels parallely to build Gaussian pyramids and detect DoG Keypoints. Based on GPU list generation[3], SiftGPU then uses a GPU/CPU mixed method to efficiently build compact keypoint lists. Finally keypoints are processed parallely to get their orientations and descriptors. SiftGPU is inspired by Andrea Vedaldi s sift++[2] and Sudipta N Sinha et al s GPU-SIFT[4] . Many parameters of sift++ ( for example, number of octaves, number of DOG levels, edge threshold, etc) are also available in SiftGPU. The shader programs are dynamically generated according to the parameters that user specified. SiftGPU also includes a GPU exhaustive/guided sift matcher SiftMatchGPU. It basically multiplies the descriptor matrix on GPU and find closest feature matches on GPU. Both GLSL and CUDA implementations are provided. )

压缩包中的算法使用moment matching和MLE估计矩阵的广义高斯分布参数，推荐一下。(Compression package using the moment matching algorithms and the estimated matrix of MLE parameters of generalized Gaussian distribution, recommend.)