CS_ROMP

otsu算法实现，可以自适应获取阈值，对图像进行二值化。里面配有图像均衡化的程序一起使用，效果更好(otsu algorithm, you can get adaptive threshold for image binarization. Which is equipped with image-based program used in conjunction with a balanced, better)

图像二值化，采用Niblack算法，采用Matlab编写，可以做个参考。(It accomplishes the binary work to an imge, using Niblack algorithm.)

image processing for hand guesture

说明：  文简要介绍了指纹识别的基本步骤，分别是指纹图像预处理、指纹特征提取、指纹匹配(This paper briefly introduces the basic steps of fingerprint recognition, which are fingerprint image preprocessing, fingerprint feature extraction and fingerprint matching)

比较好的东西，留着待用，可用于水质检测的测量参考~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~(Good stuff, keep aside ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~)

基于双目视觉的三维重建，包含了重建过程中的基本步骤。(Binocular vision-based three-dimensional reconstruction, including the reconstruction of the basic steps of the process.)

说明：  将小波和各向异性扩散结合，对超声图像进行去噪。效果较好(The combination of wavelet and anisotropic diffusion for ultrasonic image denoising. Better)

视频车辆检测，主要是介绍视频中的车辆运动目标的检测和跟踪计数(The detection of video vehicle mainly introduces the detection and tracking of moving targets in video)

DCT在图像重构，压缩感知以及稀疏表示中的应用(DCT in image reconstruction, compressed sensing and sparse representation of the application)

说明：  有数字1和2的图片各四十张，利用mat lab读取图片并将其二值化，得到只由0和1表示的矩阵，根据数字的不同特征，选择两个特征值，用来对分类器进行训练，最后用剩下的5个1和5个2来进行测试，看分类器是否可以正确的对数据进行分类。(Figures 1 and 2 pictures of the 40, using mat lab picture and secondly, the value of reading, and received only by 0 and 1, said matrix, according to the number of different features, select the two characteristic values, used to classifier training, and finally with the remaining 5 1 and 5 2 to carry out tests to see whether the classifier can correctly classify the data.)