pre_processing

国外的一个车牌识别程序，主要是基于颜色特征提取分割的，内置神经网络。(A license plate recognition program abroad, mainly segmentation based on color feature extraction, built-in neural networks.)

运用Soble,,Roberts算子,Prewitt算子,Log算子,Canny算子j进行边缘检测 (Using Sobel ,, Roberts operator, Prewitt operator, Log operator, Canny edge detection operator )

基于IDL的HJ_1A 高光谱HSI图像条带噪声去除方案研究(Based the IDL' s HJ_1A hyperspectral HSI image strips with noise removal solutions for research)

图像处理的峰值信噪比计算程序，简单精确，直接算出值(PSNR calculation program image processing, simple accurate, direct calculation value)

最新的用matlab实现的ＳＰＩＨＴ算法，实现对图像的高性能压缩。(Matlab using the latest achievement of SPIHT, the realization of high-performance image compression.)

多维OTSU阈值分割方法，能够实现二维图像多阈值分割(Multidimensional OTSU thresholding methods, able to achieve the two-dimensional image multi-threshold segmentation)

说明：  运动目标识别，采用背景差分方法。背景图像由均值法获得。里面的视频换成前几帧换成纯背景效果能更好一点(Moving target identification, using the background difference method. Background image obtained from the mean. Which replaced the previous video frame replaced by pure background a little better results)

光伏逆变系统中的最大功率点跟踪算法，采用的是变步长的扰动观察法，可以快速收敛(mppt method using variable step size perturb and observe method, it can converge faster.)

CBCT图像fdk重建,预投影、投影滤波、重建演示，功能强大(it s about the fdk rec for CBCT，forward projection、filter projection、rec demo)

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