shuangyuzhi

使用C++和CUDA编写的双边滤波器。在平滑图像的同时可以保持边界(Using bilateral filter the C++ and CUDA written. Boundary can be kept in the smooth image while)

基于最大类间方差准则的阈值分割算法。其基本思想是对像素进行划分，通过划分得到的各类之间的距离达到最大，来确定合适的门限。(Based on the maximum between-cluster variance criteria threshold segmentation algorithm. The basic idea is to divide pixels, obtained through the division of the distance between the various types of maximum, to determine the appropriate threshold.)

一个简单小波能量谱程序，可分析出信号的能量分布百分比。(A simple little wave energy spectrum program)

《图像处理的偏微分方程方法》随书光盘完整版 本光碟中包含五个文件夹。 （1）视频剪辑：可供教学演示，其中， two_cells 是采用改进的变分水平集方法，实现GAC模型图像分割的演化过程； denoissing 是利用P_M方程，对图像平滑去噪的演化过程 curve_linear_heat_flow 是利用FT实现的闭合曲线的线性热流演化过程。 （2）二值图像：其中的图像可供形态学图像处理实验用，也可通过提取对象的边界，供曲线演化实验使用。 （3）灰度图象和彩色图像：其中的图像，可以作为图像分割，平滑滤波，反差增强，彩色增强以及图像放大等实验的素材。 （4) MATLAB程序：其中包含10余个MATLAB程序或（函数）的源代码。程序中所作的注释，与书中关于对应算法的描述是一致的。 本光碟中的所有内容，仅供教学和研究参考。(" Image Processing Based on PDE" CD with the book contains the full version of the disc five folders. (1) Video clip: for teaching demonstration, which, " two_cells" is improved variational level set methods to achieve the evolution of GAC model image segmentation " denoissing" is the use of P_M equation, the evolution of image smoothing denoising process " curve_linear_heat_flow" is the use of a closed curve FT achieve a linear heat evolution. (2) binary image: one of the images for morphological image processing experiments, it can also be obtained by extracting the object boundary curve evolution for experimental use. (3) gray-scale images and color images: images which can be used as image segmentation, filtering, contrast enhancement, color enhancement and image amplification test material. (4) MATLAB Program: which includes more than 10 or MATLAB program (function) of the source code. Comments made in the program, and a description of the boo)

边缘检测，并分割，以不同颜色标示。站内有其matlab实现，这是对应的c++代码。(Edge detection and segmentation, marked with different colors. Inside the station are the matlab realize, This is corresponding c++ code.)

精心收集的几个去噪算法，包括基于视觉的非线性去噪、BLS_GSM算法、NL-Bayes图像去噪、KSVD去噪等，内容为核心代码，需要配置完善。 (Denoising algorithm of several carefully collected, including visual based nonlinear denoising, BLS_GSM algorithm, NL-Bayes image denoising, KSVD denoising, the content as the core code, the need to improve the allocation of. )

仿射变换来实现旋转 (线性变换)，平移 (向量加)，缩放操作 (线性变换)(Affine transformations are implemented by rotation (linear transformation), translation (vector addition), scaling operation (linear transformation))

将一副图像进行rgb分离，并将R G B 的各个分量显示出来。(the sepration of rgb and show the sepration )

图像质量评价，熵、平均梯度、边缘强度、方差等(Image quality evaluation, entropy, average gradient, edge strength, variance, etc.)

局部二进制模式，LBP，是已被用于纹理特征的一个 分类。在本文中，提出了一种基于使用这些功能的方法 检测缺陷图案的面料。在培训阶段，在第一个步骤LBP算子是 施加到无缺陷织物样品，逐个象素和参考的所有的行（列） 特征矢量的计算。那么这个图像被分为Windows和LBP算子是 应用这些窗口的每一行（列）。根据与参考比较 特征向量一个合适的阈值，无缺陷的窗户被发现。在检测阶段中，一个 测试图像被划分成的窗户，并使用阈值时，有缺陷的窗口可以 检测到。该方法简单，灰度不变。由于其简单性， 线上实现是可能的。(Local Binary Patterns, LBP, is one of the features which has been used for texture classification. In this paper, a method based on using these features is proposed for detecting defects in patterned fabrics. In the training stage, at first step LBP operator is applied to all rows (columns) of a defect free fabric sample, pixel by pixel, and the reference feature vector is computed. Then this image is divided into windows and LBP operator is applied to each row (column) of these windows. Based on comparison with the reference feature vector a suitable threshold for defect free windows is found. In the detection stage, a test image is divided into windows and using the threshold, defective windows can be detected. The proposed method is simple and gray scale invariant. Because of its simplicity, online implementation is possible as well. )