http://hdl.handle.net/10397/20 Search the Channel search http://repository.lib.polyu.edu.hk/jspui/simple-search http://hdl.handle.net/10397/5700 Title: Secure routing in multi-hop wireless networks<br/><br/>Authors: Zhou, Jie<br/><br/>Abstract: Secure routing protocols play an essential role for ensuring security in multi-hop wireless networks. Specifically speaking, the entire network could be paralyzed by misdirecting routing control messages, which could lead to lower network throughput, frequent packet loss and eavesdropping. Thus routing protocols should be secure enough to defend from attack, yet optimal enough to ensure routing performance. Most existing work on secure routing does not consider routing performance, nor does it adequately address the issues of providing users with information integrity and confidentiality. Moreover, current attack detection approaches make strong assumptions and require extra hardware support. In this research work, we study and propose solutions to address these challenging issues. We make the following original and significant contributions. Firstly, we propose a Security Extended Optimised Link State Routing protocol (SE-OLSR) to guarantee the integrity, confidentiality and freshness of current OLSR. Previous routing protocols focus on improving performance with the assumption the wireless environment is friendly and trustworthy. However, the multi-hop wireless network is vulnerable to numerous attackers. Thus, we adopt basic security techniques to encrypt the routing packets, in order to ensure the packets received by the destination node are the original ones sent by the source node. At the same time, a digital signature and hash values are used to guarantee the packets are the latest ones to prevent replay attacks. We implement the SE-OLSR on the Linux platform to identify its accuracy, and then transplant this secure routing protocol to mesh routers T902 and laptops to establish a Wireless Mesh Network (WMN) testbed.; Secondly, we analyse the impact of wormhole attacks and develop a countermeasure for attack detection based on a real testbed. Although many works have been done on detecting wormhole attacks, few of them actually evaluated their solutions on a testbed to consider real network conditions. In order to fill this gap, we set up a WMN testbed for studying wormhole attacks through comprehensive experiments. Some existing approaches used RTT to detect wormhole attacks. However, from both theoretical analysis and experimental results, we observed that the standard deviation of round trip time (stdev(RTT)) is a more efficient metric than RTT to identify wormhole attacks. Accordingly, we propose a new algorithm called Neighbour-Probe-Acknowledge (NPA) to detect wormhole attacks. Compared with existing works, NPA does not need time synchronisation or extra hardware support. Moreover, it achieves a higher detection rate and a lower false alarm rate than the methods using RTT under different background traffic load conditions. Finally, we propose an Optimal Secure Routing (OSR) protocol to find a secure path resilient to active attack with the best routing performance. Traditional routing protocols are designed to efficiently find paths containing high quality links in assumed trust environments. Although several routing schemes have recently been proposed as defence from attack, with increasing attention on security issues in the application of multi-hop wireless networks, only a few of these have considered routing performance. To fill this gap, we have designed a new secure routing protocol OSR taking into consideration routing performance optimisation. OSR relies on a trusted third party, Trust Clearance Center (TCC), which utilises game theory to calculate and assign a trust value for each node according to its utility report behaviour. We prove that this TCC is able to detect malicious nodes and segregate them from the network when they try to launch attacks. Therefore, optimal paths can be discovered by OSR without any utility cheating. Through extensive simulations, we demonstrate that OSR can effectively discover optimal paths with a high detection rate and a low false alarm rate. Furthermore, we observe that the behaviour of active attacks can be comprehensively formulated by using game theory. To the best of our knowledge, this is the first piece of work that adopts game theory to deal with problems that jointly consider security and routing performance.<br/><br/>Description: xvii, 94 p. : ill. ; 30 cm.; PolyU Library Call No.: [THS] LG51 .H577M COMP 2012 Zhou http://hdl.handle.net/10397/5699 Title: Intelligent texture-based pattern search, classification and interpolation for woven fabric design<br/><br/>Authors: Zheng, Dejun<br/><br/>Abstract: In the cognitive process of design activity, fabric designers conceive the color and texture composition not individually, but as an ensemble of tones, shades and tints that are created in the texture patterns of yarn and fiber materials. Perceptual features of natural textures as well as fabric textures have been extensively studied in the existing literature. However, no thorough investigation of the cognitive texture features of woven patterns in fabric design has been conducted so far. The present research uses cognitive informatics models to study fabric texture features in the process of woven fabric design. It provides a comprehensive framework to facilitate selecting and designing the fabric textures in the design process. The research framework comprises cognitive fabric feature analysis and fabric texture operations in fabric pattern design, namely, fabric search, pattern classification, and woven texture interpolation with color theme-based texture synthesis. A novel object-attribute-relation (OAR) model is used to study fabric texture digitization and texture feature analysis. A relation between the high-level cognitive features and low-level perceptual features of fabric patterns in design activity is described. The cognitive features in fabric design are used to develop fabric texture operations. Examples of how cognitive features can be used to perform texture selecting and synthesizing tasks are given. There are three major contributions of this study to existing fabric texture analysis and research. (1) The study reduces the gap between the cognitive features of fabric textures in the design activity and the perceptual features of the textures in material operations. (2) New approaches for fabric pattern design are developed based on the cognitive color theme and interpolated woven patterns. (3) The research findings illustrate that fabric texture digitization methods and cognitive feature extraction in design activity are major factors in developing effective fabric texture operations.<br/><br/>Description: 210 p. : ill. (some col.) ; 30 cm.; PolyU Library Call No.: [THS] LG51 .H577P COMP 2012 Zheng http://hdl.handle.net/10397/5698 Title: Regularized robust coding and dictionary learning for face recognition<br/><br/>Authors: Yang, Meng<br/><br/>Abstract: How to represent the object and how the object representation should be learnt are very fundamental problems in pattern classification tasks, for example, face recognition (FR). As one of the most visible research topics in computer vision, machine learning and biometrics, robust FR to occlusions, misalignment and various variations (e.g., pose, expression and illumination) is still a very challenging problem after many years’ investigation. Recently, the sparse representation theory has been rapidly developed and successfully used in solving various inverse problems such as image reconstruction. Efforts have also been made in using sparse representation for signal classification. In particular, by coding a testing face sample as a sparse linear combination of the training samples and classifying it by evaluating which class leads to the minimum coding residual, sparse representation based classification (SRC) leads to very interesting results for FR. The success of SRC greatly boosts the research of sparsity based classification and the associated dictionary learning techniques. Though SRC has shown promising performance in robust FR, there are still many problems to be further addressed. What is the working mechanism of SRC? What is the role of l₀ or l₁ norm sparsity in it? How to extract effective features to improve the accuracy and speed of SRC? How to design a robust representation fidelity term to handle various outliers? How to train a dictionary to improve classification? In this thesis, we aim to answer these questions with tools from statistical learning, convex optimization, and pattern classification. It is widely believed that the l1-norm sparsity constraint on the coding coefficients plays a key role in the success of SRC. In this thesis, however, it is shown that the collaborative representation mechanism (i.e., using all training samples to collaboratively represent the testing sample) is much more crucial than the l1-norm sparsity of coding coefficients to the success of face classification. A new framework, namely collaborative representation based classification (CRC), is then established and discussed conceptually and experimentally. CRC has various instantiations by applying different norms to the coding residual and coding coefficient, while SRC is a special case of it. It is further shown that l₂-regularizatoin of coding coefficients in CRC could achieve similar performance to or better performance than l₁-regularization and have higher computational efficiency.; We then discuss the use of local features to improve the performance and speed of SRC. We present a Gabor feature based robust representation and classification (GRRC) scheme with Gabor occlusion dictionary (GOD) learning. It is shown that the use of Gabor feature and GOD not only improves the FR accuracy but also reduces significantly the computational cost in handling face occlusion. This part of work also indicates that the appropriate representation model (e.g., the regularization and dictionary) has a close relationship to the feature of the involved signals, which should be considered in designing effective representation models. The third major contribution of this thesis is the development of regularized robust coding (RRC) for FR. In RRC, a robust representation fidelity term is proposed to handle various outliers in face images. RRC is a maximum a posterior solution by assuming that the coding residual and the coding coefficient are respectively independent and identically distributed. An iteratively reweighted regularized robust coding algorithm is developed to solve the RRC model efficiently. Extensive experiments on representative face databases demonstrate that the RRC is much more effective and efficient than state-of-the-art sparse representation based methods in dealing with face occlusion, corruption, lighting and expression changes, etc. Finally, we discuss the problem of dictionary learning (DL) for sparse representation based pattern classification, and propose a novel Fisher discrimination dictionary learning (FDDL) scheme. Based on the Fisher discrimination criterion, a structured dictionary, whose dictionary atoms have correspondence to the class labels, is learnt so that the reconstruction residual after sparse coding can be used for pattern classification. Meanwhile, the Fisher discrimination criterion is imposed on the coding coefficients so that they have small within-class scatter but big between-class scatter. A new classification scheme associated with the proposed FDDL method is then presented by using both the discriminative information in the reconstruction residual and sparse coding coefficient. The proposed FDDL is extensively evaluated on benchmark image databases in comparison with existing sparsity and DL based classification methods.<br/><br/>Description: xvi, 179 p. : ill. ; 30 cm.; PolyU Library Call No.: [THS] LG51 .H577P COMP 2012 Yang http://hdl.handle.net/10397/5697 Title: Texton encoding based texture classification and its applications to hand-back skin texture analysis<br/><br/>Authors: Xie, Jin<br/><br/>Abstract: Real world objects have various types of texture surfaces. With the increasing demands of image understanding and object recognition in many computer vision applications, texture classification has been receiving considerable attention, and plenty of texture classification methods have been proposed in the past decades. However, how to efficiently represent texture and extract texture features is still a challenging problem in texture image analysis and classification. In this thesis, we investigate this problem and propose new solutions for efficient texture feature extraction, representation and classification. As an interesting application, we also apply the proposed methods to hand back skin texture analysis. First, we present a sparse representation (SR) based dictionary learning method to learn a dictionary of textons for texture image representation. In traditional texton learning based texture representation approaches, texton learning is usually implemented by the K-means clustering method. However, the K-means clustering process may not be able to well characterize the intrinsic feature space of textons, which is often embedded into a low dimensional manifold. To improve the representation accuracy and capability, we propose to use the dictionary learning method under the SR framework to learn a dictionary of textons. Consequently, the SR coefficients of the texture image over the dictionary of textons are used to construct the histograms for classification. The proposed SR based texton dictionary learning method yields better performance than the traditional K-means clustering based texture classification methods.; We further propose an efficient texton encoding based texture classification scheme. The scheme consists of four stages: texton dictionary learning, texton encoding, feature description and classification. In the stage of texton dictionary learning, a regularized least square based texton learning model is proposed. Compared with the texton learning based on SR or K-means clustering, the proposed model is much more accurate than the K-means clustering while being much more efficient than the SR to implement. Meanwhile, we propose a fast texton encoding method to code the texture feature over the learned dictionary. Consequently, two types of texton encoding induced statistical features, coefficient histogram and residual histogram, are extracted for classification. The proposed method, namely texton encoding induced statistical feature (TEISF), is validated on three representative benchmark texture datasets: CUReT, KTH_TIPS and UIUC. The experimental results demonstrate that TEISF outperforms state-of-the-arts, especially when the number of the training samples is small. Finally, we study the hand back skin texture (HBST) pattern classification problem for personal identification and gender classification. A specially designed HBST imaging system is developed to capture the HBST images, and an HBST image dataset is established, which consists of 1920 images from 80 persons (160 hands). Then the proposed texton learning based texture analysis methods are applied to the established HBST dataset, and the experimental results demonstrate that HBST is very useful to aid human identity identification and gender classification. As a kind of specific texture images, the established HBST dataset is rather challenging and provides a good platform to evaluate various texture classification algorithms.<br/><br/>Description: xiii, 116 p. : ill. ; 30 cm.; PolyU Library Call No.: [THS] LG51 .H577P COMP 2012 Xie