ROC--AUC

实现运动模糊图像的非盲卷积 分区域去模糊 有用(Implementation of motion blurred image blind deconvolution is useful to fuzzy areas)

基于otsu的自适应阀值canny边缘检测(adaptive canny edge detection based on otsu)

说明：  使用python语言实现多张图像的拼接，并且处理拼接之后的裂缝和黑边。(Use python language to achieve splicing of multiple images, and deal with cracks and black edges after splicing.)

本代码主要是基于HSV的阴影检测及消除，分别提取前景及背景图像，进行色彩空间转换。HSV空间类似人类感觉色彩的方式，可以更加准确地识别阴影，并保持在计算上简单。(This code is mainly based on the HSV shadow detection and elimination, extract the foreground and the background image, respectively, for color space conversion. HSV space is similar to the ways the human feel color, can more accurately identify the shadow, and keep it simple in calculation. )

Solutions for Digital Image processing Gonzalez - Solution Manual (3rd edition)

说明：  本程序是基于小波和盒维数的车型识别程序，可以选择不同车型，有GUI界面，有图片，有程序，能运行，相信初学者一定能够获益。(This program is based on the wavelet and box dimension of the vehicle type recognition program, you can choose different models, GUI interface, pictures, programs, can run, I believe beginners will benefit.)

在matlab环境下基于数学形态学的图像去噪，传统去噪只选用一种结构元素，去噪效果并不理想，这种去噪方法实现简单，功能强大，无论对于高斯、椒盐、维纳等噪声都去有很强的去噪效果，且算法简单。(In the matlab environment based on mathematical morphology image denoising, denoising only use traditional elements of a structure, de-noising effect is not ideal, this denoising method is simple and powerful, both for the Gaussian, salt and pepper, Wiener such noise are to have a strong denoising effect, and the algorithm is simple.)

BP神经网络图像分类程序,代码很好懂，适合初学者。样本选的不是很大。(BP neural network image classification procedures, code easy to understand for beginners. Sample selected is not great.)

傅立叶变换，等距离采样，等角度采样，轮廓提取，形态处理(Fourier transform, equidistant sampling, in terms of sampling, contour extraction, morphological processing)

EDLines是一种快速直线检测算子，2012年在ICCV上提出，也是目前处理直线检测最快的算法之一，该算法包含三个步骤：（1）边缘提取：利用Edge Drawing (ED)算法[28,29]从灰度图像中提取边缘片段；（2）线段检测：利用最小二乘法提取直线段；（3）线段确认：遵循Helmholtz定律，从已提取的直线段中摒弃虚假线段。EDLines算法的优越性得益于Edge Drawing (ED)算法能够从灰度图像中准确、快速、稳定地提取出光滑、完整的边缘片段。Edge Drawing (ED)算法包含以下步骤： （1）采用size=5*5,σ=1的高斯核对灰度图像进行平滑滤波，去除噪声； （2）采用一种常用的梯度算子，如Prewitt、Sobel或Scharr等计算平滑后图像中每个像素点的梯度幅度和梯度方向； （3）将梯度图中邻域内幅度最大的像素点标记为锚点，这些锚点成为图像边缘点(edge elements)的概率很大； （4）将相邻的锚点连接成边缘线。从一个锚点起始，ED利用相邻像素的梯度幅度和方向在梯度为最大值的锚点之间游走。 (Edge Drawing (ED) is our recently-proposed, novel, fast edge detection algorithm. What makes ED stand out the existing edge detectors, e.g., Canny, is the following: While the other edge detectors give out a binary edge image as output, where the etected edge pixels are usually independent, discontinuous entities ED produces a set of edge segments, which are clean, contiguous, i.e., connected, chains of edge pixels. Thus, while the output of the other edge detectors requires urther processing to generate potential object boundaries, which may not even be possible or result in inaccuracies ED not only produces perfectly connected object boundaries by default, but it also achieves this in blazing speed compared to other edge detector.)