A motion retargeting algorithm based on model simplification

A new motion retargeting algorithm is presented, which adapts me motion capture data to a new character. To make the resulting motion realistic, the physically-based optimization method is adopted. However, the optimization process is difficult to converge to the optimal value because of high complexity of the physical human model. In order to address this problem, an appropriate simplified model automatically determined by a motion analysis technique is utilized, and then motion retargeting with this simplified model as an intermediate agent is implemented. The entire motion retargeting algorithm involves three steps of nonlinearly constrained optimization： forward retargeting, motion scaling and inverse retargeting. Experimental results show the validity of this algorithm.     

Improved Genetic Algorithm Application in Textile Defect Detection

Based on an efficient improved genetic algorithm, a pattern recognition approach is represented for textile defects inspection. An image process is developed to automatically detect the drawbacks on textile caused by three circumstances： break, dual, and jump of yams. By statistic method, some texture feature values of the image with defects points can be achieved. Therefore, the textile defects are classified properly. The advanced process of the defect image is done. Image segmentation is realized by an improved genetic algorithm to detect the defects. This method can be used to automatically classify and detect textile defects. According to different users＇ requirements, different types of textile material can be detected.     

An improved double-threshold method based on gradient histogram

This paper analyzes the characteristics of the output gradient histogram and shortages of several traditional automatic threshold methods in order to segment the gradient image better. Then an improved double-threshold method is proposed, which is combined with the method of maximum classes variance, estimatingarea method and double-threshold method. This method can automatically select two different thresholds to segment gradient images. The computer simulation is performed on the traditional methods and this algorithm and proves that this method can get satisfying result.     

ORDERED-OBJECT-ORIENTED METHOD:A NEW APPROACH OF SAMPLE PART CALCULATION AND DESIGN

This paper proposed a new approach of sample part classification and design, a so called Or-dered-object-oriented method (O-O-O method). Based on the theory of neural networks, fuzzy clustering algorithm and adaptive pattern recognition, O-O-O method can be used to classify and design the sample parts automatically. The basic theory, the main step as well as the characteristics of the method are analysed. The construction of the ordered object in application is also presented in this paper.     

A RBF Network Learning Scheme Using Immune Algorithm Based on Information Entropy

A hybrid learning method combining immune algorithm and least square method is proposed to design the radial basis function(RBF) networks. The immune algorithm based on information entropy is used to determine the structure and parameters of RBF nonlinear hidden layer, and weights of RBF linear output layer are computed with least square method. By introducing the diversity control and immune memory mechanism, the algorithm improves the efficiency and overcomes the immature problem in genetic algorithm. Computer simulations demonstrate that the RBF networks designed in this method have fast convergence speed with good performances.     

An atlas-based fuzzy connectedness method for automatic tissue classification in brain MRI

A framework incorporating a subject-registered atlas into the fuzzy connectedness (FC) method is proposed for the automatic tissue classification of 3D images of brain MRI. The pre-labeled atlas is first registered onto the subject to provide an initial approximate segmentation. The initial segmentation is used to estimate the intensity histograms of gray matter and white matter. Based on the estimated intensity histograms, multiple seed voxels are assigned to each tissue automatically. The normalized intensity histograms are utilized in the FC method as the intensity probability density function (PDF) directly. Relative fuzzy connectedness technique is adopted in the final classification of gray matter and white matter. Experimental results based on the 20 data sets from IBSR are included, as well as comparisons of the performance of our method with that of other published methods. This method is fully automatic and operator-independent. Therefore, it is expected to find wide applications, such as 3D visualization, radiation therapy planning, and medical database construction.     

LINGUISTIC SELF-ORGANIZING PROCESS CONTROLLER USING GENETIC ALGORITHM

A linguistic self-organizing controller using genetic algorithm is presented, whose control policy is able to generate, develop and improve. The scaling factors can be chosen automatically.Optimizing the scaling factors by genetic algorithm instead of trial or experimental method which is often used in conventional linguistic self-organizing controller eliminates the drawback of an exhausive search of the GE*GC*GU space by human operator, and also produces the better system response and a set of better control rules. A number of simulations on linear dynamic systems as well as non-linear systems such as second order process with a random disturbance, third order process with time lags and the cart-pole balancing problem etc. are described in this paper, which shows that the controller has strong adaptive properties and gives better performance than that of the conventional linguistic self-organizing controller.     

Research of Dynamic Competitive Learning in Neural Networks

Introduce a method of generation of new units within a cluster and a algorithm of generating new clusters. The model automatically builds up its dynamically growing in ternal representation structure during the learning process. Comparing model with other typical classification algorithm such as the Kohonen‘s self-organizing map. the model realizes a multilevel classification of the input pattern with an optional accuracy and gives a strong support possibility for the parallel computational main processor. The idea is suitable for the high-level storage of complex datas structures for object recognition.     

A New Genetic Algorithm Based on Niche Technique and Local Search Method

The genetic algorithm has been widely used in many fields as an easy robust global search and optimization method. In this paper, a new generic algorithm based on niche technique and local search method is presented under the consideration of inadequacies of the simple genetic algorithm. In order to prove the adaptability and validity of the improved genetic algorithm, optimization problems of multimodal functions with equal peaks, unequal peaks and complicated peak distribution are discussed. The simulation results show that compared to other niching methods, this improved genetic algorithm has obvious potential on many respects, such as convergence speed, solution accuracy, ability of global optimization, etc.     

一种基于集合划分的鲁棒性自适应模糊聚类分割算法

模糊C均值算法(FCM)是图像分割最常用的算法之一,这种方法需要提前确定初始聚类中心和聚类数.为此,提出了一种新的自适应模糊聚类算法(AFCM),AFCM算法中构造的观察矩阵、判断矩阵和集合划分可以自动确定合适的聚类数.为了得到更好的图像分割效果,采用核距离作为相似性度量,提出了一种鲁棒性自适应模糊C均值算法(RAFCM).实验结果表明,与FCM算法相比,AFCM和RAFCM算法不仅能自动地确定聚类数目,还可以得到更好的图像分割质量.     

基于免疫粒子群优化的模糊C均值聚类算法

把免疫系统的免疫信息处理机制引入到粒子群优化（PSO）算法中，并与模糊C均值（FCM）算法相结合提出一种新的模糊聚类算法．新算法用免疫粒子群优化算法代替FCM算法的基于梯度下降的迭代过程，使算法具有较强的全局搜索能力，很大程度上避免了FCM算法易陷入局部极小的缺陷，同时也降低了FCM算法对初始值的敏感度．采用对当基思想初始化种群，获得更优的初始候选解，提高算法聚类过程中的收敛速度．以UCI机器学习数据库中的两组数据集为研究对象，实验结果表明，该算法优于基于PSO的模糊C均值聚类算法和FCM算法．     

基于马氏距离的模糊聚类优化算法——KM-FCM

为了解决以欧氏距离作为相似性准则的传统模糊聚类算法对多维数据处理不利的问题,采用马氏距离代替欧氏距离,对基于马氏距离的模糊聚类算法进行优化研究,以增强基于马氏距离的模糊聚类算法的聚类效果和能力。通过构造启发式搜索与k-means算法结合的初始优化方法,利用可以自动调节最佳聚类数的有效性函数,提出了一种优化算法KM-FCM,并将此新算法与FCM,FCM-M,M-FCM聚类算法在3个标准数据集上进行了实验。结果表明,KM-FCM算法有效,聚类精度比FCM,FCM-M,M-FCM高,对高维数据聚类识别能力强,具有全局优化作用,并且聚类个数无需提前设定。新算法可为基于马氏距离的模糊聚类算法的优化提供参考。     

基于人工免疫粒子群优化算法的动态聚类分析

模糊C-均值聚类算法受初始化影响较大,在迭代时容易陷入局部极小值。将粒子群优化算法与模糊G-均值聚类算法相结合,提出一种新颖的动态聚类算法。该算法利用人工免疫思想改进粒子群优化过程,在很大程度上避免了粒子群算法和聚类算法早熟现象的发生,全局搜索能力和局部搜索能力优于同类算法。利用聚类理论中的经验规则kmax≤√n确定聚类数k的搜索范围,在最优粒子基础上进化新一级种群,该方案可有效提高算法的收敛速度。两组数据的仿真实验表明,新算法优于传统模糊C-均值聚类算法,具有收敛速度快和解的精度高的特点。     

基于自适应差异演化的模糊聚类算法

在聚类分析中,模糊C-均值聚类(FCM)是一种广泛应用的算法,但由于它是基于梯度下降的,本质上是一种局部搜索算法,容易陷入局部极小值,且对初始值很敏感.本文提出一种基于自适应差异演化的模糊聚类算法(FCBADE),该算法利用差异演化良好的全局搜索能力,在全局范围内寻找最优解的近似解,然后由FCM算法在该近似解的周围进行局部搜索,最终得到全局最优解.同时为减少手工设置控制参数对DE算法的影响,采用自适应方式调整DE算法的控制参数.实验结果表明,该算法不仅有效克服了FCM算法易陷入局部极小值的缺点,而且明显地避免了对初始化选值敏感性的问题,也有较快的收敛速度.     

基于Fuzzy c-means算法聚类有效性函数的纹理分割

Fuzzy c-means(FCM)算法用于图像分割是一种非监督模糊聚类后再标定的过程．本文利用聚类有效性函数对Fuzzy c-means算法的聚类结果进行评价，从而获得最优的聚类结果，较好地解决了Fuzzy c-means算法的一些不足，如聚类数目无法自动确定、其聚类结果是否最优．最后，利用纹理图像分割实验验证了该算法的有效性．     

一种快速模糊聚类分割算法

本文把区域生长技术与FCM聚类方法结合起来,提出了一种快速FCM聚类分割算法.由于大大减少了参与聚类的样本数目,有效地提高了FCM聚类分割的速度.通过对遥感TM图像的分割实验,本算法比经典FCM聚类算法速度提高三倍以上.     

基于遗传算法的改进模糊C均值算法在入侵检测中的应用

 为克服模糊C均值（FCM）算法对初始化极为敏感且容易陷入局部最优的缺点,将遗传算法和改进的模糊C均值聚类算法相结合,并以检测率和误检测率作为入侵检测算法性能评价的指标,对FCM、改进的FCM、基于遗传的改进FCM 3种聚类算法的入侵检测性能进行仿真分析。仿真实验表明,结合遗传和FCM两种算法的混合算法能够实现优势互补。由于该算法结合了遗传算法,使整个算法的复杂度增加。从入侵检测看,通过增加处理时间而提高了入侵检测率。     

基于遗传的改进模糊C均值入侵检测方法

为了克服模糊C均值(FCM)算法对初始化极为敏感且容易陷入局部最优的缺点,将遗传算法和改进的模糊C均值聚类算法相结合,并且以检测率和误检测率作为入侵检测算法性能评价的指标,对FCM、改进的FCM和基于遗传的改进FCM三种聚类算法的入侵检测性能进行仿真分析.结果表明:基于遗传的改进FCM算法(GIFCM),检测率有所提高,而误检测率有所下降.该算法应用于异常入侵检测是可行而有效的.     

基于FCM和标记分水岭的粘连岩石颗粒图像分割

模糊C均值算法可利用图像的多种特征值进行准确的图像分割,但不能分割粘连物体;传统的分水岭分割算法能够获得准确的物体边缘轮廓,但容易造成过分割.为了解决这个问题,提出基于FCM和标记分水岭的粘连图像分割.该方法首先对原始彩色图像中值滤波后进行基于LUV颜色空间的FCM聚类;对聚类后的图像用形态学方法去杂质、空洞填充后进行距离变换;然后根据距离变换图像找出局部最大值,得到种子图像;最后对距离变换图像进行基于标记的分水岭分割,得到最终的分割图像.该方法对粘连岩石颗粒图像进行分割,取得了较好的实验效果.