搜索资源列表
HistogramEqualization
- 直方图均衡化,包括动态直方图均衡化,全局直方图均衡化,局部直方图均衡化,以及绘制图像的直方图 其中动态直方图均衡化用A dynamic histogram equalization for image contrast enhancement 只取x=0情况-Histogram equalization, including dynamic histogram equalization, global histogram equalization, local histogram equaliz
project
- The eight-node quadrilateral element is a two-dimensional finite element with both local and global coordinates
CPSO
- 混沌粒子群算法,求代价函数问题,可以避免粒子群算法陷入局部最优,求取全局最优。代码含代价函数,可作为例子理解。-Chaos particle swarm optimization, seeking cost function problems, avoid getting into local optimum particle swarm algorithm, obtaining the global optimum. Code containing cost function can be u
msOS_V0.12_20150910
- msos 2015年9月11日 1、Gui增加单精度浮点类型GuiDataTypeFloatDec,字符串直接显示类型GuiDataTypeString,采用sprintf解析数字,转换成字符显示,ModifyTextBoxData函数全新设计,支持对单精度数据类型float加减。 2、App和Menu中增加了单精度浮点数据类型的例子和直接字符串显示的例子。 3、增加data和menu数据类型,在系统层定义了data的全局指针AppDataPointer,这样便于在系统设
mization
- Recently more research works are focused on multi-objective particle swarm optimization algorithm (MOPSO) due to its ability of global and local search for solving multi-objective optimization problems (MOOPs) however, most of existing MOPSOs can
greedy
- 1)编程实现背包问题贪心算法和最小生成树prim算法。通过具体算法理解如何通过局部最优实现全局最优,并验证算法的时间复杂性。 2)输入5个的图的邻接矩阵,程序加入统计prim算法访问图的节点数和边数的语句。 3) 将统计数与复杂性函数所计算的比较次数比较,用表格列出比较结果,给出文字分析。 4)背包问题的实验数据如下表:n=8,m=110 -1) programming to implement the knapsack problem greedy algorithm and
manualhist
- 灰度局部拉伸,当部分图像灰度太暗或者太亮的时候,可采取局部灰度拉伸而不是全局灰度拉伸-Local tensile gray, as part of the image grey is too dark or too bright, can take local gray stretch rather than global gray stretch
bi-image
- 图像二值化matlab程序源代码。实现局部变量与全局变量的图形灰度分割。-Binarization matlab program source code. Achieve local variables and global variables grayscale graphics division.
glcmaa1
- 标准的GLCM纹理分析往往没有得到好的结果,除非大量使用全局类(使用大量的类,带来其他问题)。使用本地类可以帮助,但结果对噪声很敏感。本程序采用加权区域采样大大提高全局和局部灰度共生矩阵纹理分析的结果。-Standard GLCM texture analysis is often not good , except for a large number of global classes (which use a large number of classes to bring other p
c-language-collection
- 这是一个学习c语言函数方面的程序合集,主要讲述了全局变量和局部变量的区别。-This is a learning function c language collection aspects of the program, mainly about the difference between global variables and local variables.
Defoging-based-on-hist
- 本算法为基于直方图均衡化的图像去雾算法的改进算法,在改进中利用了自己编写的改进全局直方图均衡化算法和内置的局部直方图均衡化函数分别进行图像去雾,最后对两者进行适当加权。同时改进算法中引进了明度参数进行加权计算得出另一种改进结果。-This algorithm is based on the image histogram equalization algorithm defogging improved algorithm, improving the use of their preparat
simulate
- 使用DC算法求解非凸函数的最优化问题。可以确保局部最优解,有时收敛到全局最优-DC algorithm using optimization problem of non-convex function. Ensure local optima, sometimes converge to the global optimum
saliency-dection--bayesian
- 基于贝叶斯概率框架的图像显著性检测,与局部和全局两方面探讨-Image saliency detection is based on bayesian,and research local contrast and global rarity.
hierachial_ensemble_of_global_local
- code for face identification by analysing local and global features
vns-mpso
- 将NSGA-II 的理念融入粒子群中,并加入保存优秀解的机制,提出MPSO算法。针对MPSO 易陷入局部极值的缺点,加入变邻域机制,通过随机的破坏旧解和重建新解,找到全局最优解,以达到帮助粒子跳出局部极值的目的,提 出VNS-MPSO 算法。-Will the NSGA- II concept into particle swarm, and join save good solution mechanism, MPSO algorithm is put forward. Against d
ABC
- 人工蜂群算法是模仿蜜蜂行为提出的一种优化方法,只需要对问题进行优劣的比较,通过各人工蜂个体的局部寻优行为,最终在群体中使全局最优值突现出来,有着较快的收敛速度。-Artificial colony algorithm is to imitate the bee behavior put forward an optimization method,Only need to compare advantages and disadvantages of problem, Through the l
The-Cuckoo-SearchThe-Cuckoo-Search
- 布谷鸟搜索(CS)算法是根据生物界中布谷鸟的寄生繁殖机理而提出的一种仿生智能优化算法,由于布谷鸟搜索算法具有优秀的全局搜索和局部搜索能力,并且控制参数少,收敛速度快-The Cuckoo Search (CS) algorithm is a bionic intelligent optimization algorithmbased on the mechanism of biological reproduction in parasitic cuckoo proposed. Dueto th
altificial-bee-colonyalgorithm
- 人工蜂群算法是模仿蜜蜂行为提出的一种优化方法,是集群智能思想的一个具体应用,它的主要特点是不需要了解问题的特殊信息,只需要对问题进行优劣的比较,通过各人工蜂个体的局部寻优行为,最终在群体中使全局最优值突现出来,有着较快的收敛速度。-Artificial bee colony algorithm is an optimization technique to mimic the behavior of bees make is thinking of a particular cluster of
deepsaldet-master
- 基于深度学习的图像显著性检验,在cnn框架的基础上,采用全局与局部的多上下文模型,取得了最优效果。-Significant test image based on the depth of learning, based on cnn framework on the use of global and local multi-context model, and achieved the best results.
Face-Recognition-code
- 首先建立一个标准的人脸模板,由包含局部人脸特征的子模板构成, 然后对一幅输入的人脸图像进行全局搜索,基于人脸灰度模板的模式匹配计算与标准人脸模板中不同部分的相关系数,通过预先设置的最小匹配门限来判断该图像窗口中是否包含人脸。-First, establish a standard template face by face feature contains the local sub-template structure,Then a face image input global sear