Contact-free and pose-invariant hand-biometric-based personal identification system using RGB and depth data

Hand-biometric-based personal identification is considered to be an effective method for automatic recognition. However, existing systems require strict constraints during data acquisition, such as costly devices,specified postures, simple background, and stable illumination. In this paper, a contactless personal identification system is proposed based on matching hand geometry features and color features. An inexpensive Kinect sensor is used to acquire depth and color images of the hand. During image acquisition, no pegs or surfaces are used to constrain hand position or posture. We segment the hand from the background through depth images through a process which is insensitive to illumination and background. Then finger orientations and landmark points, like finger tips or finger valleys, are obtained by geodesic hand contour analysis. Geometric features are extracted from depth images and palmprint features from intensity images. In previous systems, hand features like finger length and width are normalized, which results in the loss of the original geometric features. In our system, we transform 2D image points into real world coordinates, so that the geometric features remain invariant to distance and perspective effects. Extensive experiments demonstrate that the proposed hand-biometric-based personal identification system is effective and robust in various practical situations.     

Membrane automata with priorities

In this paper the one-way P automata with priorities are introduced. Such automata are P systems where the membranes are only allowed to consume objects from parent membranes, under the given conditions. The result of computation of these systems is the set of multiset sequences consumed by skin membrane into the system. The rules associated in some order with each membrane cannot modify any objects, they can only move them through membrane. We show that P automata with priorities and two membranes can accept every recursively enumerated language.     

The optimization design of collision detection for barrage games

The collision detection is of great importance in almost every game, whether among the objects or between the object and the scene .If the author don＇t detect collisions, objects will intersect each other or object will intersect the scene. In this paper, the author present two algorithms that high-speed detects the collision detection between moving bullet and role with unknown trajectories in 2D environment. The objects for collision detection are bounded by the axis-aligned rectangles or circles. The known information such as world coordinate system, collision object coordinate system and collision detection area coordinate system etc, are stored in the data files in advance. The data control systems load those information into the collision detection module to handle the collision among the roles and bullets. We set coordinate values of rectangular center and four vertexes or the center point of a circle and use the distance between two points or the distance from a point to a line to see whether the object＇s vertexes are enclosed in the other object. If it is true, there is a collision occurring. We improved the algorithm to make the player share the scene of running through the bullet cluster with skill and ease while avoiding being shot.     

Novel infrared and visible image fusion method based on independent component analysis

The goal of infrared （IR） and visible image fu- sion is for the fused image to contain IR object features from the IR image and retain the visual details provided by the visible image. The disadvantage of traditional fusion method based on independent component analysis （ICA） is that the primary feature information that describes the IR objects and the secondary feature information in the IR image are fused into the fused image. Secondary feature information can de- press the visual effect of the fused image. A novel ICA-based IR and visible image fusion scheme is proposed in this paper. ICA is employed to extract features from the infrared image, and then the primary and secondary features are distinguished by the kurtosis information of the ICA base coefficients. The secondary features of the IR image are discarded during fu- sion. The fused image is obtained by fusing primary features into the visible image. Experimental results show that the pro- posed method can provide better perception effect.     

PHC: A Fast Partition and Hierarchy-Based Clustering Algorithm

Cluster analysis is a process to classify data in a specified data set.In this field,much attention is paid to high-efficiency clustering algorithms.In this paper,the features in the current partition-based and hierarchy-based algorithms are reviewed ,and a new bierarchy-based algorithm PHC is proposed by compbining advantages of both algorithms,which uses the cohesion and the colseness to amalgamate the clusters.Compared with similar algorithms,the performance of PHC is improved,and the quality of clustering is guaranteed.And both the features were proved by the theoretic and experimental analyses in the paper.     

时空数据库索引机制研究

Spatio-temporal database manages the large amount of spatial objects that change over time.It is necessary to query the spatio-temporal objects of the past and the current and to anticipate the future of spatio-temporal objects.It is important to design an efficient index mechanism for accessing the spatio-temporal data efficiently.The paper analyzes the features of the spatio-temporal objects,studies the methods of spatio-temporal index mechanisms,classifies the index mechanisms,and discusses the key technologies of spatio-temporal indexes.And it also presents the index methods of STADBS that we are studying.     

Reflection and Refraction on Implicit Surfaces

Implicit surfaces are often used in computer graphics. They can be easily modeled and rendered, and many objects are composed of them in our daily life. In this paper, based on the concept of virtual objects, a novel method of real-time rendering is presented for reflection and refraction on implicit surface. The method is used to construct virtual objects from real objects quickly, and then render the virtual objects as if they were real objects except for one more step of merging their images with the real objects＇ images. Characteristics of implicit surfaces are used to compute virtual objects effectively and quickly. GPUs （Graphics Processing Units） are used to compute virtual vertices quickly and further accelerate the computing and rendering processes. As a result, realistic effects of reflections and refractions on implicit surfaces are rendered in real time.     

A Component Mining Approach,to Incubate Grid Services in Object-Oriented Legacy Systems

This paper describes an approach for Grid service component mining in object-oriented legacy systems, applying Software clustering, architecture recovery, program slicing and wrapping techniques to decompose a legacy system, analyse the concerned components and integrate them into a Grid environment. The resulting components with core legacy code function in a Grid service framework.     

Optimization leads to symmetry

The science of complexity studies the behavior and properties of complex systems in mture and human society.Particular interest has been put on their certain simple common properties. Symmetry is one of such properties. Symmetric phenomena can be found in many complex systems. The purpose of this paper is to reveal the internal reason of the symmetry.Using some physical systems and geometric objects,the paper shows that many symmetries are caused by optinfizadon under certain criteria. It has also been revealed that an evolutional process may lead to symmetry.     

Feature selection on probabilistic symbolic objects

In data analysis tasks, we are often confronted to very high dimensional data. Based on the purpose of a data analysis study, feature selection will find and select the relevant subset of features from the original features. Many feature selection algorithms have been proposed in classical data analysis, but very few in symbolic data analysis （SDA） which is an extension of the classical data analysis, since it uses rich objects instead to simple matrices. A symbolic object, compared to the data used in classical data analysis can describe not only individuals, but also most of the time a cluster of individuals. In this paper we present an unsupervised feature selection algorithm on probabilistic symbolic objects （PSOs）, with the purpose of discrimination. A PSO is a symbolic object that describes a cluster of individuals by modal variables using relative frequency distribution associated with each value. This paper presents new dissimilarity measures between PSOs, which are used as feature selection criteria, and explains how to reduce the complexity of the algorithm by using the discrimination matrix.     

遗产软件对象标识方法

该文讨论了目前遗产软件对象标识方法存在的问题,在簇分析的基础上提出了概念分析方法,并分别从数据库应用系统和非数据库应用系统两个角度考虑,结合这两类系统的特点提出并讨论了如何构造适合于概念分析的项目特征表,给出了利用项目特征表生成概念的概念构造算法,最后将概念分析方法与簇分析方法进行了比较。     

一种利用模块内聚性的对象抽取方法

引入子程序-类型关系图来表示程序中类型和子程序之间的关系,讨论了模块内聚性的几个度量准则,并分析了增删子程序对模块内聚度的影响.在此基础上,给出了基于模块内聚性的对象抽取算法.     

Distributed architecture technologies

Moving from a legacy architecture to one that uses distributed objects has both complexities and rewards. IT managers who are planning this move face several distribution issues that require them to make crucial choices involving a wide range of languages, operating systems, networking protocols, and applications. The paper presents a review of the various types of architectures     

Self-organization of Dynamic Object Features Based on Bidirectional Training

This paper presents a method to self-organize object features that describe object dynamics using bidirectional training. The model is composed of a dynamics learning module and a feature extraction module. Recurrent Neural Network with Parametric Bias (RNNPB) is utilized for the dynamics learning module, learning and self-organizing the sequences of robot and object motions. A hierarchical neural network is linked to the input of RNNPB as the feature extraction module for self-organizing object features that describe the object motions. The two modules are simultaneously trained through bidirectional training using image and motion sequences acquired from the robot's active sensing with objects. Experiments are performed with the robot's pushing motion with a variety of objects to generate sliding, falling over, bouncing and rolling motions. The results have shown that the model is capable of self-organizing object dynamics based on the self-organized features.     

基于J2EE分布式环境的再工程方法

给出基于J2EE分布式环境的遗留系统再工程框架。应用改进的层次聚类算法提取系统组件,能够方便地将代码取出以构建分布式系统。给出适用于J2EE 分布式环境的组件接口启发式规则和模块部署策略。实现企业遗留系统到J2EE分布式系统的再设计过程,验证该框架的强壮性、实用性和通用性。     

基于数据依赖图的主域变量识别方法*

随着企业/组织中大量遗留系统的产生,遗留系统的业务逻辑提取技术也受到越来越多的关注。对于提取业务逻辑,主域变量是一个很好的入口点。在应用领域中,主域变量对应着重要的业务对象,分析主域变量的状态变化以及主域变量间的关系可以获得大部分的业务逻辑。但现今,国内外对于主域变量识别技术的研究大多只提到它的重要性,并没有提出如何提取主域变量的具体方法。给出了一种基于数据依赖图(DDG)的主域变量识别方法,并将该方法运用到一大型遗留系统的业务逻辑提取中。实践证明该方法大大提高了提取效率,并有效地降低了出错的可能性。     

A middleware for industry

This paper describes an innovative distributed framework for monitoring and control of large-scale systems by integrating heterogeneous smart objects, the world of physical devices, sensors and actuators, legacy devices and sub-systems, cooperating to support holistic management [1]. Its featured Service Oriented Architecture (SOA) exposes objects’ capabilities by means of web services, thus supporting syntactic and semantic interoperability among different technologies, including SCADA systems [23]. Wireless Sensor and Actuator Network (WSAN) devices and legacy subsystems cooperate while orchestrated by a manager in charge of enforcing a distributed logic. Particularly crafted for industrial networks are new middleware services such as dynamic spectrum management, distributed control logic, object virtualization, WSANs gateways, a SCADA gateway service, and data fusion transport capability. In addition, new application oriented objects such as shop floor, manufacturing line, welding station, robots, and cells have been introduced in the middleware. The combination of such objects and previous modules offers a new and flexible industry oriented middleware. A second contribution is in the form of traffic analysis conducted at the floor level. It shows the dominance of some end systems such as PLCs, the presence well behaved almost constant traffic made up of small packets.     

Integrate software agents and CORBA in computational grid

This paper presents an Agent-based Computational Grid (ACG), which applies the concept of CORBA and agent to computational grid. The ACG system is used to implement a uniform higher level management of the computing resources and services on the Grid, and provide users with a consistent and transparent interface for accessing such services. In ACG grid, grid services are implemented by CORBA or by grid agent. Grid agents and CORBA objects will interact with each other to achieve user's service request. Our solution is the creation of a bridge between the CORBA and grid agents. The solution provides with the opportunity of considering an agent as a CORBA service and accessing CORBA services even from a grid agent. Thus, in AGC grid, existing legacy systems can be easily exploited as grid services. In this paper, firstly, the features of ACG grid are described, and then the design and implementation are given. Finally, some conclusions are given.     

An end-to-end neural network for detecting hidden people in images based on multiple attention network

Camouflaged people like soldiers on the battlefield or even camouflaged objects in the natural environments are hard to be detected because of the strong resemblances between the hidden target and the background. That’s why seeing these hidden objects is a challenging task. Due to the nature of hidden objects, identifying them require a significant level of visual perception. To overcome this problem, we present a new end-to-end framework via a multi-level attention network in this paper. We design a novel inception module to extract multi-scale receptive fields features aiming at enhancing feature representation. Furthermore, we use a dense feature pyramid taking advantage of multi-scale semantic features. At last, to locate and distinguish the camouflaged target better from the background, we develop a multi-attention module that generates more discriminative feature representation and combines semantic information with spatial information from different levels. Experiments on the camouflaged people dataset show that our approach outperformed all state-of-the-art methods.