资源列表
T_ThetaFit
- 基于T熵的多阈值分割,实现了灰度图像的自动转换,以及对灰度图像的二阈值和三阈值的分割算法-T entropy-based multi-threshold segmentation grayscale image automatically converted, and the threshold grayscale images and three threshold segmentation algorithm
log_ThetaFit
- 基于对数熵的多阈值分割,实现了灰度图像的自动转换,以及对灰度图像的二阈值和三阈值的分割算法-T entropy-based multi-threshold segmentation grayscale image automatically converted, and the threshold grayscale images and three threshold segmentation algorithm
zhishu_ThetaFit
- 基于指数熵的多阈值分割,实现了灰度图像的自动转换,以及对灰度图像的二阈值和三阈值的分割算法-Algorithm based on the the index entropy threshold segmentation, to achieve the automatic conversion of grayscale images, as well as the threshold grayscale images and three threshold values
auto_divide
- 一种新的多阈值分割算法,可根据参数设定提取获取多个不同的阈值-A new multi-threshold segmentation algorithm, extracted according to the parameters set for different threshold
dfanning
- Dfanning包，简单的使用IDL中的各种颜色。本程序包含于dfaaning包中-Dfanning package, Easy color definition using in IDL.
cgsolve(1)
- 共轭梯度下降法，Ax = y,求x.矩阵A为共轭对称稀疏矩阵,cgsolve matlab 程序-Conjugate gradient descent method, Ax = y, seeking x. Matrix A is conjugate symmetric sparse matrix, cgsolve matlab program
BP
- 基于matlab R2010a的BP神经网络在遥感图像分类中的应用源代码-Application source code matlab R2010a BP neural network-based remote sensing image classification
MFC_OpenGL
- 该程序用于在Visual Stdio 2005环境的MFC下使用OpenGL技术编程的框架-Using OpenGL technology under MFC
main
- image processing，应用fisher原理，进行人脸识别，应用了Opencv的函数库-image processing, principle of application fisher, face recognition, the application of the Opencv the function library
Watershed
- 分水岭算法Matlab实现。如果图像中的目标物体是连在一起的，则分割起来会更困难，分水岭算法经常用于处理这类问题，通常会取得比较好的效果。-Matlab implementation of watershed algorithm.If the object in the image together, then split up and it will be more difficult, the watershed algorithm often used to deal with such
main_orlyang_optproj
- 众所周知，特征抽取是模式识别中最基本的问题之一，抽取有效的鉴别特征是解决识别问题的关键。特征抽取即为将原始样本映射（或变换）到某一低维特征空间，得到最能反映分类本质的低维样本特征，有效地实现分类问题。-function wrong=Near_classify(final_sample,ln)
main_eigenface_proj
- 众所周知，特征抽取是模式识别中最基本的问题之一，抽取有效的鉴别特征是解决识别问题的关键。特征抽取即为将原始样本映射（或变换）到某一低维特征空间，得到最能反映分类本质的低维样本特征，有效地实现分类问题。-function wrong=Near_classify(final_sample,ln)