laserengraver插件

对静态图像应用canny算法提取边缘特征(The edge feature is extracted by canny algorithm of static image)

说明：  基于IDL语言，使用珠海一号内蒙古地区样例数据、珠海一号贵阳省高光谱数据、Landsat5济南上下幅TM数据（用于拼接验证），实现文件基本操作、遥感图像预处理、高光谱数据处理、生态评价、最大似然法分类、K-Means分类等遥感图像初步处理功能。(Based on IDL language, using Zhuhai No.1 Inner Mongolia area sample data, Zhuhai No.1 Guiyang province hyperspectral data, landsat5 Jinan upper and lower TM data (for splicing verification), the preliminary processing functions of remote sensing image, such as file basic operation, remote sensing image preprocessing, hyperspectral data processing, ecological evaluation, maximum likelihood classification, K-means classification, etc.)

基于MATLAB语言模拟复眼成像，同时模拟不同的深度信息(Simulate compound eye imaging based on MATLAB language, and simulate different depth information.)

说明：  高光谱图像数据集，Pavia University scene该数据是高光谱图像处理中常用的数据之一，对高光谱图像算法性能的验证具有通用性(Hyperspectral image data set, Pavia University scene This data is one of the commonly used data in hyperspectral image processing, and it has universality to verify the performance of hyperspectral image algorithm)

matlab 图像处理方面的经典书籍，值得初学者仔细认真的学习(matlab image processing aspects of classic books, worthy of serious study carefully beginners)

这是一个asm主动形状模型的函数箱，里面都是全是源码(This is an active shape model asm function boxes, which are all source)

基于FFT以及次谐波的两种相位屏仿真方法源程序；主函数用于显示相位屏的二维和三维图像(FFT-based and subharmonic two phase screen simulation method source program; the main function is used to display two-dimensional and three-dimensional images of the phase screen.)

标记分水岭的matlab程序。分水岭变换就是指将原图像转换为一个标记图像, 其中所有属于同一集水盆的点均被赋予同一个标记, 并用一个特殊的标记来标识分水岭上的点(Marking a watershed in the matlab program. Watershed transform refers to the original image is converted to a Tagged Image, which all belong to the same set of points were given a basin with a marker, and a special marker to identify the point of a watershed)

说明：  我们提出了一个简单、灵活和通用的对象实例分割框架。我们的方法能有效检测图像中的对象，同时为每个实例生成高质量的 segmentation mask。这种被称为 Mask R-CNN 的方法通过添加用于预测 object mask 的分支来扩展 Faster R-CNN，该分支与用于边界框识别的现有分支并行。Mask R-CNN 训练简单，只需在以 5fps 运行的 Faster R-CNN 之上增加一个较小的 overhead。此外，Mask R-CNN 很容易推广到其他任务，例如它可以允许同一个框架中进行姿态估计。我们在 COCO 系列挑战的三个轨道任务中均取得了最佳成果，包括实例分割、边界对象检测和人关键点检测。没有任何 tricks，Mask R-CNN 的表现优于所有现有的单一模型取得的成绩，包括 COCO 2016 挑战赛的冠军。(Mask R-CNN code by HeKaiming)

LSB信息隐藏算法，就是通常把信息隐藏在图像像素的最后一位，可能对你们有帮助(LSB information hiding algorithm, the information is usually hidden in the image pixels of the last one, you may have to help)