▍1. periodic-3d-tongzhou-resonanter
---三维fdtd程序,采用周期性边界条件(3D fdtd procedures, periodic boundary conditions)
---三维fdtd程序,采用周期性边界条件(3D fdtd procedures, periodic boundary conditions)
利用ENVI/IDL,计算多幅图像的各个像元的平均值。并忽略空缺值(Use ENVI/IDL, calculate the average of each pixel of multiple images. And ignores the value of vacancies)
自己曾经做的一个项目,基于几何特征的模式识别。可以有效的识别等边三角形,矩形,六角形 和圆形。 基于c++和OpenCV 编写的程序。是学习OpenCV的好代码。 图像处理&模式识别。(Marksdetection for equilateral triangles,rectangle, regular hexagon, special orthogonal polygons and circles Based on C++ and OpenCV good source code for image processing and mark detection)
实现图像颜色识别分块实现图像颜色识别分块(Block of image color recognition)
形态学pathopenings的实现,对线特征提取等图像处理有令人惊奇的效果。(Morphological pathopenings the realization of the line feature extraction and other image processing have surprising effects.)
形态学pathopenings的实现,对线特征提取等图像处理有令人惊奇的效果。(Morphological pathopenings the realization of the line feature extraction and other image processing have surprising effects.)
说明: 实现多张图像的三维可视化过程,可以用于各类三维模型的建立过程。(Realize the 3D visualization process of multiple images)
说明: 遥感高光谱图像处理,实现丰度估计;传统sansul算法(remote sensing,image processing,abundance estimation method)
处理Gamma乘性噪声的PPB方法,考虑了非局部patch的相似性,可处理SAR图像去噪。(The PPB method for multicative noise removal, which based on the Probabilistic Patch similarity.)
处理Gamma乘性噪声的PPB方法,考虑了非局部patch的相似性,可处理SAR图像去噪。(The PPB method for multicative noise removal, which based on the Probabilistic Patch similarity.)
对于一个二值图像骨架化之后进行边缘平滑,滤波,效果非常不错,适合于任何二值图片(After a binary image is skeletonized, it is smoothed and filtered. The effect is very good. It is suitable for any binary image.)
1.选择一幅图像,对该图像进行DCT块操作(将图像分成8×8小块,对每个小块进行DCT变换)。 2.利用屏蔽矩阵对DCT系数进行区域选择,然后进行逆变换(IDCT),合成原图像,计算合成图像的PSNR。 3.选择一小波函数,对一幅图像进行分解,显示各变换系数,观察其规律,并进行小波逆变换,合成原图像。 (1. Select an image, the image DCT block operations (the image is divided into 8 × 8 small pieces of each small piece for DCT transform). 2. The use of shielding on the DCT coefficient matrix of regional choices, and then inverse transform (IDCT), synthesis of the original image, calculating the synthetic image PSNR. 3. To select a wavelet function, decomposition of an image to show the transform coefficients, to observe its laws, and inverse wavelet transform, the original synthetic image.)
三维人脸数据库FRGC V1. 0,2.0包括图像的深度数据和纹理,格式分别保存为:abs和ppm 读取abs数据中的深度z轴数据,保存为480*640的矩阵,进而进行数据处理研究。并且贴ppm纹理,便于观察。 (Three-dimensional face database FRGC V1. 0,2.0 depth data including images and textures, formats were saved as: abs abs data and ppm reads depth z-axis data, save it as a 480* 640 matrix, and then studied for data processing . And paste ppm texture, easy to observe.)
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.)
python语言,使用卷积神经网络的特征做图像检索(image retrieval using CNN)
说明: 利用其中不同的光谱匹配算法实现光谱匹配,内部还含有相关数据(Using different spectral matching algorithms to achieve spectral matching, there are also relevant data inside)