noise

基于特征匹配的英文印刷字符识别，里面有实验所需的图片和具体的代码(English printed character recognition based on feature matching, which contains the pictures and specific code needed for the experiment)

sift 的c++代码。。。。。。。。。。。。(sift c++ code)

数字水印技术检测，可以对图像加入水印或者从图像中检测出水印(digital watermark detection technology, the image watermarking or from the images detected watermark)

avi视频读取，与播放，并将图像的每一帧保存下来(avi video reads, plays with, and saves each frame of the image)

图像二值化算法，试用效果还不错，欢迎大家试用(Improved Image and Text Binarization Algorithm)

RunSFM中作者写的纹理映射的应用程序(RunSFM the authors write texture mapping application)

hit-miss方法下的图像骨架提取，很好用(hit-miss method of image skeleton extraction, very good use)

图像检测的算法，Faster R-CNN算法，先对整张图像进行卷积计算，然后通过感兴趣区域池化层(RoI Pooling Layer)将选择性搜索算法推荐出来的候选区域和卷积网络计算出的特征映射图进行融合，得到候选区域对应的特征矢量，这种共享卷积计算的操作极大地减少了卷积计算的次数。而且这些特征矢量的维度统一，方便后续的分类工作。通过感兴趣区域池化层处理卷积特征，并将得到的特征送往两个并行计算任务进行训练，分类和定位回归。通过这些方法和改进的框架，Fast R-CNN 用更短的训练和测试时长，取得了比 R-CNN 更好的效果(Faster R-CNN algorithm first convolutes the whole image, then fuses the candidate regions recommended by the selective search algorithm and the feature mapping maps calculated by the convolution network through the RoI Pooling Layer to get the corresponding feature vectors of the candidate regions, which greatly reduces the number of convolution calculations. Moreover, the dimension of these feature vectors is unified, which facilitates the subsequent classification work. The convolution feature is processed by the pooling layer of the region of interest, and the obtained feature is sent to two parallel computing tasks for training, classification and positioning regression. Through these methods and improved framework, Fast R-CNN uses shorter training and testing time and achieves better results than R-CNN.)

在本文件中，我主要研究通过行人的表观特征进行识别，例如颜色、纹理等等。用matlab GUI 编写了程序，对行人进行匹配 (Pedestrian recognition of the inter-camera is intelligent surveillance camera network a key research direction. Match the pedestrian different camera, you can cross the pedestrian track of the camera, the expansion of the monitoring horizon, at the same time can have a clearer grasp of the behavior of pedestrians in the entire surveillance area. Different cameras, different lighting conditions, the pedestrian position and a different scale, shelter, etc., making the pedestrian match challenging. In this document, I study to identify by pedestrian apparent characteristics such as color, texture, and so on.)

修改过的pca-sift程序 可以正常运行(Modified pca-sift program runs)