图像处理

人工智能 caffe 用与ssd yolo(Artificial intelligence SSD Yolo)

VC++图像处理程序设计(杨淑莹)第四章_灰度变换源码(VC++ image processing program design (Yang Shuying) Chapter _ gray transform source)

利用数学形态学进行图像去噪，实现了自适应图像去噪的目的，希望能够给大家帮助(Using mathematical morphology for image denoising and achieve the purpose of the adaptive image denoising, hoping to give you help)

关于深度玻尔兹曼机的工具箱，可以进行图像的分类和识别。(About Deep Boltzmann Machine Toolbox,which you can use for image classification and identification.)

图像检索中经典的SIFT方法matlab实现，由NTU的大牛撰写，做了些批注。(SIFT for image retrieval，feature extraction and matching)

retinex算法的一个源代码，用于图像增强处理，能比较好的提高对比度(retinex an algorithm source code for image enhancement, to better enhance the contrast)

计算两幅图像之间的交叉熵，自己编的比较简单和大家分享。(Calculate the cross-entropy between the two images, their own series is relatively simple and to share.)

基于图像对比度和波段相关性的波段选择算法，适用于高光谱图像的特征选择(Bands selection algorithm based on image contrast and correlation of bands for hyperspectral image feature selection)

背景差分法运动目标检测，建立背景模型，然后使用当前模型与背景模型相减，再和阈值相比较，比阈值大的即判断为有运动目标，比阈值小的即判断为没有运动目标，阈值大小可以自己适当调试，根据经验值设置最佳阈值。(Background difference method is used for moving target detection and setting up background model, then using current model and background model subtracting, and comparing with threshold, it is judged to have moving target compared with the threshold value, which is smaller than threshold. The size of threshold can be adjusted properly, and the best threshold is set according to experience value.)

Adaptive Perona–Malik Model Based on the Variable Exponent for Image DenoisingThis paper introduces a class of adaptivePerona–Malik (PM) diffusion, which combines the PM