HOG

用于图像处理的陷波滤波器. m文件，有例子说明。(Notch filter notch filter. M file, there are examples.)

功能简单的截图，可以像qq那样截图，并有图片处理功能(Simple screenshots, like QQ screenshots, and image processing capabilities)

采用了Harrtraining和离子滤波算法实现了拥挤人群人头计数，非常有用。VC++和Opencv开发，采用Oepncv中的Harrtraining训练一个分类器即可运行(Human detection and tracking in high density crowds is an unsolved problem. Standard preprocessing techniques such as background modeling fail when most of the scene is in motion. We integrate human detection and tracking into a single framework, and in- troduce a conrmation-by-classication method to estimate condence in a tracked trajectory, track humans through occlusions, and eliminate false positive detections.)

说明：  水平集边缘检测代码，利用了变分法进行优化和处理，实现了图像的快速边缘检测(Level set edge detection code is optimized and processed by using variational method, and fast edge detection of image is realized.)

说明：  基于c#运动控制及图像处理项目源码，有兴趣可以看看(Based on C# motion control and image processing project source code)

这是一个比较全面的傅里叶变换，例子中含有测试的图片，能让人更加明白傅里叶变换的处理效果。(This is a more comprehensive Fourier transform, the example contains a picture of the test, can make people more aware of the Fourier transform of the treatment effect.)

说明：  张正相机标定，用c++编程，亲证有用，里面有实际的图片，大家可以直接俄使用(Zhang zheng method it is very useful for camera detecting and it contains many pictures i hope you will get help from it)

Matlab 实现的带阻滤波器设计。基于高斯带阻滤波器。实现冈萨雷斯《数字图像处理》第五章的实例。(Matlab implementation of the band stop filter design. Based on Gaussian band-stop filter. Achieve Gonzalez, " Digital Image Processing" Chapter V of the instance.)

[MATLAB] 安捷伦示波器波形离线FFT分析谐波含量 在现场用示波器记录波形，保存为CSV文件，可以使用本程序进行离线分析。 直流量，交流量，偏移量，谐波次数都可以完美分析。 内含帮助文件，适合MATLAB2009以上([MATLAB] Agilent oscillograph waveform offline FFT analysis of harmonic content Oscillograph waveform is recorded on the scene and saved as CSV file. This program can be used for off-line analysis. Direct flow, AC quantity, offset and harmonic number can be perfectly analyzed. Contain help files, suitable for more than MATLAB2009)

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.)