Discrimination of similar handwritten numerals based on invariant curvature features

This paper studies the discrimination of similar handwritten numerals based on invariant curvature features. High-order B-splines are used to calculate the curvature of the contours of handwritten numerals. The concept of a distribution center is introduced so that a one-dimensional periodic signal can be normalized as shift invariant. Consequently, the curvature of the contour of a character becomes rotation invariant. To reduce the dimension of the features, wavelet basis decomposition is used to produce more compact features. Finally, artificial neural network (ANN) and support vector machines (SVM) are employed to train the features and design classifiers of high recognition rates.     

Adaptive normalization of handwritten characters using global/localaffine transformation

This paper introduces an adaptive or category-dependent normalization method that normalizes an input pattern against each reference pattern using global/local affine transformation (GAT/LAT) in a hierarchical manner as a general deformation model. Also, the normalization criterion is clearly defined as minimization of the mean of nearest-neighbor interpoint distances between each reference pattern and a normalized input pattern. Optimal GAT/LAT is determined by iterative application of weighted least-squares fitting techniques. Experiments using input patterns of 3,171 character categories, including Kanji, Kana, and alphanumerics, written by 36 people in the cursive style against square-style reference patterns show that the proposed method not only can absorb a fairly large amount of handwriting fluctuation within the same category, but the discrimination ability is greatly improved by the suppression of excessive normalization against similarly shaped but different categories. Furthermore, comparative results obtained by the conventional shape normalization method for preprocessing are presented     

Pair-wise discrimination based on a stroke importance measure

The pair-wise discriminator is a binary classifier that verifies the outcome of the recognizer if it belongs to a class in a pre-defined confusion pair database. It is difficult to discriminate a pair of characters that are very similar in shape except for a small difference, because the small difference can be overridden by the writing variation. This paper proposes a pair-wise discrimination method that discriminates similar characters by focusing on the structural difference between the two characters. It discriminates a pair of characters by comparing their matching scores between the input character and the models of the two characters. When the stroke matching scores are combined to compute the overall matching score, each stroke is assigned a weight to reflect its importance in discriminating the character pair. By assigning large weights to the discriminative strokes, the difference between the characters is emphasized. The stroke weights are systematically obtained by a neural network training algorithm. In the experiments, the recognition performance was significantly improved by applying the proposed method.     

Feature based robust watermarking using image normalization

This paper presents a robust watermarking scheme based on feature point detection and image normalization. Firstly some stable feature points are detected from the original image using the proposed multiresolution feature point detection filter. Then, image normalization is applied to the disks centered at these feature points. The watermark is embedded in the subband coefficients of DFT domain of each disk separately. And the watermark detection uses the correlation between the watermark embedding coefficients and the original watermark, and does not need the original image. The proposed scheme combines the advantages of feature point detection and image normalization, which can achieve strong robustness to signal processing and geometrical distortions. The experimental results also demonstrate good performance of the proposed scheme.     

基于模块化分析的动态系统重要度测量方法

为了解决关键系统灵敏性分析中的状态空间爆炸问题,提出一种基于模块化分析、适用于动态系统的重要度测量方法.将系统故障树分解为多个层次不同的独立模块,在此基础上引入微扰法的思想,对BI(Birnbaum importance measure)重要度指标进行扩展.提出相对重要度的概念,根据各独立模块的类型,分别求解相对重要度,利用相对重要度进行组合计算,求出系统级重要度.将该方法应用于一个实际高可靠计算机系统,分析结果显示该方法能够提供一个可信的重要度测量.     

Reliability evaluation and component importance measure for manufacturing systems based on failure losses

Little work has been done to assess the reliability of a vital system like the manufacturing system. In this article, a novel and effective system reliability evaluation method in terms of failure losses has been proposed for manufacturing systems of job shop type, and then the failure losses based component importance measure (CIM) is used for importance analysis of equipment. The former indicates the present system reliability situation and the latter points the way to reliability improvement efforts. In this scheme, the problem is described and modeled by a dynamic directed network. Consider that the actual processing time of machines is to contribute to failure occurrence, it is used to calculate the failure times and failure losses. The obtained total failure times and failure losses of the system are applied to evaluate its reliability. Techniques to estimate two kinds of failure losses based CIMs are presented. They offer guidelines to realize system reliability growth cost-effectively. A case study of a real job shop is provided as an example to demonstrate the validity of the proposed methods. Comparison to other commonly used methods shows the efficiency of the proposed methods.     

基于场势模型的网络节点重要性综合度量方法

针对网络节点的重要性受到多种因素影响的问题,提出一种基于场势模型的网络节点重要性综合度量方法。采用数据场模型对网络节点之间的相互作用关系进行形式化描述;根据节点的资产价值和互联节点之间的相互作用关系,综合量化节点的重要性;引入安全影响因素,通过可达性矩阵修正节点势场的可作用范围。理论分析与实验结果表明,该方法能够更客观准确地度量节点的重要性,有效区分边缘节点的差异性,使度量结果与节点的实际重要性相吻合。     

非线性Contourlet变换和区域特征匹配的图像融合

针对图像融合中存在边缘轮廓表示不清晰和计算冗余度过高的问题.提出了将非线性估计Contourlet变换和图像区域特征相结合的融合算法.通过非线性估计保留Contourlet高频稀疏矩阵最重要系数频带,对低频区域、高频区域采用不同的区域特征策略进行图像融合.实验结果表明:该图像融合算法不仅可以提高图像融合的视觉效果和图像质量、而且可以去噪音,增强图像.     

基于字符规范化的文档图像水印算法

运用字符规范化和小波变换的知识,提出一种将文档图像分割成字符图像,再对字符图像规范化,然后将随机序列嵌入到小波图像低频系数的水印算法.根据视觉系统纹理掩蔽特性,将不同强度的水印分量嵌入到了不同的小波系数中.由于文档图像分割和规范化本身具有抗几何攻击的特性,故该方法对缩放、小角度旋转有一定的鲁棒性,实验结果表明:该方法在文档图像上比其它方法更具备优越性.     

Texture segmentation using independent-scale component-wise Riemannian-covariance Gaussian mixture model in KL measure based multi-scale nonlinear structure tensor space

This paper proposes a novel texture segmentation approach using independent-scale component-wise Riemannian-covariance Gaussian mixture model (ICRGMM) in Kullback-Leibler (KL) measure based multi-scale nonlinear structure tensor (MSNST) space. We use the independent-scale distribution and full-covariance structure to replace the covariant-scale distribution and 1D-variance structure used in our previous research. To construct the optimal full-covariance structure, we define the full-covariance on KL, Euclidean, log-Euclidean, and Riemannian gradient mappings, and compare their performances. The comparison experiments demonstrate that the Riemannian gradient mapping leads to its optimum properties over other choices when constructing the full-covariance. To estimate and update the statistical parameters more accurately, the component-wise expectation-maximization for mixtures (CEM²) algorithm is proposed instead of the originally used K-means algorithm. The superiority of the proposed ICRGMM has been demonstrated based on texture clustering and Graph Cuts based texture segmentation using a large number of synthesis texture images and real natural scene textured images, and further analyzed in terms of error ratio and modified F-measure, respectively.     

Efficient numerical simulation methods for estimating fuzzy failure probability based importance measure indices

For the problem with a fuzzy failure state which commonly exists in degradation structures and systems, the fuzzy failure probability based importance measure indices can be used to measure the effect of the input variables on the fuzzy failure probability effectively. However, the computational cost is unaffordable for estimating the indices directly. For efficiently evaluating the fuzzy failure probability based importance measure indices, this paper proposed two numerical simulation methods, i.e., the direct Monte Carlo simulation method based on the Bayesian formula (B-DMCS) and the adaptive radial-based importance sampling method based on the Bayesian formula (B-ARBIS). The two proposed methods employ the Bayesian formula to eliminate the dependence of the computational cost on the dimensionality of the input variables. Compared with the B-DMCS method, the B-ARBIS method can enhance the computational efficiency significantly due to repeatedly utilizing the same group of samples of the input variables and the strategy to adaptively search the optimal hypersphere in the safety domain. After giving the principles and implementations of the two methods, three examples are employed to validate the effectiveness of the two proposed numerical simulation methods. The results of the examples demonstrate that the effectiveness of the two proposed methods is higher than the direct Monte Carlo method, and the B-ARBIS method can improve the efficiency obviously in contrast with the B-DMCS method.

     

A quadtree normalization scheme based on cyclic translations

An image can be represented by a compact and hierarchical structure, i.e. a quadtree. The storage requirements of an image constructed by a quadtree is highly sensitive to its position. Ang and Samet [Pattern Recognition Lett. 15(1), 57–63 (1994)] proposed an algorithm capable of normalizing a quadtree in O(s²log₂s) time and O(s²) space, where s is the length of the image grid, such that the number of nodes of the quadtree after normalization can be minimal. However, s is twice as long as the length of one side of the image to be normalized. In this study, we propose a normalization scheme based on cyclic translations. The time complexity and the space requirements of this scheme have four times less than those in Ang and Samet's case. In addition, no translation is necessary to fit the image into the northwest quadrant of the grid before the process of normalization. Also, this scheme can normalize a quadtree to obtain less node numbers than that of Ang and Samet. Furthermore, if the image's four corners have the same color, the amount of reduction for node number becomes larger after cyclic translations; it can occasionally reach to 75%. The analytical and empirical results demonstrate the advantages of this scheme.     

基于正六边形区域划分的无线传感器网络动态目标跟踪

针对无线传感器网络(WSNs)目标跟踪应用中的跟踪精度与能耗问题,提出一种能量均衡消耗的目标跟踪协同算法.该算法以正六边形网格作为分簇模型,能动态地唤醒无线传感器网络中合适的簇对目标状态进行估计.同时引入了虚拟簇头的概念用于优化簇头选举策略.仿真分析表明:所提出的算法与簇内集中式算法相比不仅具有相当的估计性能,并能有效降低对簇头节点的性能要求.除此之外,通过自适应动态簇头选举策略,有效地均衡了各簇中节点能量消耗,提高了系统的健壮性.     

基于图像归一化的轮廓域数字水印算法研究

为了使Contourlet域数字水印能有效地抵抗几何攻击,提高数字水印的鲁棒性,以图像归一化理论为基础,提出了一种可有效抵抗几何攻击的Contourlet域数字图像水印方案。该方案利用基于矩的图像归一化技术和不变质心理论提取出归一化图像的重要区域,对该重要区域进行Contourlet变换,根据Contourlet变换后图像系数的特性,用奇偶量化的方法将水印信息嵌入到Contourlet变换后中频子带上。实验结果表明,该方案不仅具有很好的透明性,而且具有较强的抵抗常规信号处理及几何攻击的能力。     

Computing multiscale curve and surface skeletons of genus 0 shapes using a global importance measure

We present a practical algorithm for computing robust, multiscale curve and surface skeletons of 3D objects. Based on a model which follows an advection principle, we assign to each point on the skeleton a part of the object surface, called the collapse. The size of the collapse is used as a uniform importance measure for the curve and surface skeleton, so that both can be simplified by imposing a single threshold on this intuitive measure. The simplified skeletons are connected by default, without special precautions, due to the monotonicity of the importance measure. The skeletons possess additional desirable properties: They are centered, robust to noise, hierarchical, and provide a natural skeleton-to-boundary mapping. We present a voxel-based algorithm that is straightforward to implement and simple to use. We illustrate our method on several realistic 3D objects.     

基于字型特征的手写体汉字多分类识别的研究

针对汉字特点,提出一种基于汉字结构度和繁简度二类模态判别的多模式识别法。给出了汉字字型结构度类型的字型编码,以及汉字字型结构分解算法;对分解后的部件进行繁简度判断,依据各部件繁简度模态选择合适的特征提取算法,实现手写体汉字字型分解的多模式识别方法融合;对相似字采用两级分类的识别法,从而提高汉字的识别率和正确率。仿真实验验证了方法的有效性。     

Generalized matrix measure of switched nonlinear systems

A concept of generalized matrix measure for nonlinear systems is proposed to study the stability of switched nonlinear systems directly. Based on this concept, some sufficient conditions for the robust stability of switched nonlinear systems are derived by using the methods of cycle analysis and contraction analysis     

Facial expression synthesis based on similar faces

Multimedia Tools and Applications - Facial expression synthesis has several applications involving animation, human-computer interaction, entertainment, and training people with mental disorders....     

基于区域GAC模型的二值化水平集图像分割算法

针对测地线主动轮廓(GAC)模型进行了改进,提出了一种基于区域的GAC模型.通过构造基于区域统计信息的符号压力函数取代边界停止函数,有效解决了弱边界目标或离散状边界目标的分割问题.该模型采用二值化水平集方法实现,避免了传统实现方法水平集函数需要重新初始化为符号距离函数,从而导致稳定性差、计算量大、实现复杂等缺点.对不同类型图像的试验结果表明:该算法迭代收敛速度比GAC模型传统实现方法明显加快,且可有效防止边界泄漏,分割效果优于传统GAC模型与C-V模型.     

Improvement of collaborative filtering using rating normalization

With the advent of the Internet, the types and amount of information one can access have increased dramatically. In today’s overwhelming information environment, recommendation systems that quickly analyze large amounts of available information and help users find items of interest are increasingly needed. This paper proposes an improvement of an existing preference prediction algorithm to increase the accuracy of recommendation systems. In a recommendation system, prediction of items preferred by users is based on their ratings. However, individual users with the same degree of satisfaction to an item may give different ratings to the item. We intend to make more precise preference prediction by perceiving differences in users’ rating dispositions. The proposed method consists of two processes of perceiving users’ rating dispositions with clustering and of performing rating normalization according to such rating dispositions. The experimental results show that our method yields higher performance than ordinary collaborative filtering approach.