RGB2HSI

人脸识别手册，在里面详细的介绍了关于人脸检测的相关知识。不过是全英文的，如果有英语比较好，时间比较多愿意翻译这本书的人请留言。(Face Recognition manual inside detail on the face detection of the relevant knowledge. But is English, if English is better, more time is willing to translate this book, please post.)

点目标质量评估，一维积分旁瓣比、峰值旁瓣比(ISLR PSLR)

使用matlab代码求出不规则区域所对应的最小外接矩形(find the smallest rectantangle of unregular region with matlab)

使用frequency-tuned saliency算法计算图像的saliency值，基于此saliency值将图像中的显著区域提取出来。(Using frequency-tuned saliency saliency value of image algorithm, based on the saliency value of the significant image area extracted.)

用平均背景法去除背景，算法思想比混合高斯模型和codebook模型简单，适合提取背景变化较小的场景。用中值滤波去除掉产生的椒盐噪声(Average method to remove the background with the background, the algorithm thought codebook than the Gaussian mixture model and a simple model for extraction of small changes in background scene. With a median filter to remove salt and pepper noise generated)

说明：  在matlab下实现信号频谱分析：利用快速付里叶变换FFT得到下列信号的频谱，并绘制信号及频图形：1.长2s的方波信号，频率f=10Hz (In matlab signal spectrum analysis: the fast in leaf transform FFT get pay of spectrum, the signal and drew the signal and frequency graphics: 1. The long 2s, frequency f = square wave signal 10Hz )

舌像的梯度提取，然后进行分水岭分割，最后进行邻近区域合并，得到舌体图像。(tongue-image s watershed segmentation based on its gradient change.)

伪彩色增强的matlab程序，主要基于空间域灰度级－彩色变换,算法清晰,效果较好. (pseudo-color enhanced Matlab procedures, mainly on the spatial domain gray level-color transformation, the algorithm clear. effective.)

基于Hilbert变换的相位差测量法分析及改进 (Based on the analysis phase measurement and improvement of the Hilbert transform)

说明：  输出带连接点的匹配影像，基于opencv(Output matched image with connection points, based on OpenCV)