Tiande Guo

Singular Points Detection Based on Zero-Pole Model in Fingerprint Images

An algorithm is proposed, which combines Zero-pole Model and Hough Transform (HT) to detect singular points. Orientation of singular points is defined on the basis of the Zero-pole Model, which can further explain the practicability of Zero-pole Model. Contrary to orientation field generation, detection of singular points is simplified to determine the parameters of the Zero-pole Model. HT uses rather global information of fingerprint images to detect singular points. This makes our algorithm more robust to noise than methods that only use local information. As the Zero-pole Model may have a little warp from actual fingerprint orientation field, Poincare index is used to make position adjustment in neighborhood of the detected candidate singular points. Experimental results show that our algorithm performs well and fast enough for real-time application in database NIST-4.

Fingerprint Compression Based on Sparse Representation

A new fingerprint compression algorithm based on sparse representation is introduced. Obtaining an overcomplete dictionary from a set of fingerprint patches allows us to represent them as a sparse linear combination of dictionary atoms. In the algorithm, we first construct a dictionary for predefined fingerprint image patches. For a new given fingerprint images, represent its patches according to the dictionary by computing l0-minimization and then quantize and encode the representation. In this paper, we consider the effect of various factors on compression results. Three groups of fingerprint images are tested. The experiments demonstrate that our algorithm is efficient compared with several competing compression techniques (JPEG, JPEG 2000, and WSQ), especially at high compression ratios. The experiments also illustrate that the proposed algorithm is robust to extract minutiae.

An Efficient Algorithm for Fingerprint Matching Based on Convex Hulls

The purpose of fingerprint matching is to compare two fingerprint images and return a similarity score that represents to the probability of match between the two fingerprints. The performance of an automatic fingerprint identification system is greatly determined by its fingerprint matching algorithm. In this paper, a full fingerprint matching algorithm is presented. The main contribution of this paper is that a novel algorithm based on convex hulls for eliminating spurious matching in fingerprint matching is proposed. It is very important for improving the performance of fingerprint matching algorithm to reducing spurious matching. The algorithm is tested on a public database FVC2002 DB1_A. Experimental results show that the proposed algorithm is performed well compared with other ones.

Parallel Variable Distribution Algorithm for Constrained Optimization with Nonmonotone Technique

A modified parallel variable distribution (PVD) algorithm for solving large-scale constrained optimization problems is developed, which modifies quadratic subproblem at each iteration instead of the of the SQP-type PVD algorithm proposed by C. A. Sagastizabal and M. V. Solodov in 2002. The algorithm can circumvent the difficulties associated with the possible inconsistency of subproblem of the original SQP method. Moreover, we introduce a nonmonotone technique instead of the penalty function to carry out the line search procedure with more flexibly. Under appropriate conditions, the global convergence of the method is established. In the final part, parallel numerical experiments are implemented on CUDA based on GPU (Graphics Processing unit).

A Novel and Efficient Algorithm for Segmentation of Fingerprint Image Based on LBP Operator

Segmentation of fingerprint image is to extract the region of interest (ROI) of image and highly influences the performance of Automatic Fingerprint Identification System (AFIS). In this paper, we present a novel segmentation approach which is very different from traditional segmentation methods. It is based on local binary pattern (LBP) which has good performance on texture discrimination. The proposed algorithm is applied on the images from FVC database. Experimental results demonstrate the high efficiency and good performance of the algorithm. This method serves for minutiae detection compared with VeriFinger 6.0 published by Neurotechnology Company in 2008, and the result indicates that our algorithm leads to an improved accuracy of minutiae detection since many remaining ridges which are the residual images of the previously scanned finger are removed as background accurately.

Fingerprint Feature-Point Matching Based on Motion Coherence

Fingerprint matching is very important for automatic fingerprint recognition system (AFIS). After local structure matching, one minutia in query fingerprint may have multiple candidate matching minutiae in template fingerprint. So how to get right one-to-one matching pairs has great effect on the performance of fingerprint matching algorithm. In this paper, a global fingerprint matching algorithm is presented. The main contribution of this paper is that a novel and efficient algorithm for getting one-to-one matching pairs based on motion coherence is proposed. Motion coherence is a very useful feature for fingerprint matching. The algorithm is tested on a public database FVC2002 DB1_A and FVC2004 DB1_A. Experimental results show that the proposed algorithm is performed well compared with other ones.

Generalized Graph Regularized Non-negative Matrix Factorization for Data Representation

In this paper, a novel method called Generalized Graph Regularized Non-Negative Matrix Factorization (GGNMF) for data representation is proposed. GGNMF is a part-based data representation which incorporates generalized geometrically-based regularizer. New updating rules are adopted for this method, and the new method convergence is proved under some specific conditions. In our experiments, we evaluated the performance of GGNMF on image clustering problems. The results show that, with the guarantee of the convergence, the proposed updating rules can achieve even better performance.

Algorithm and Convergence of MST Problem for Energy Efficient Routing in Wireless Sensor Networks

The rapid development of the theory and application makes it imperative to find the best strategies to improve the energy efficiency of wireless sensor networks. In this paper, we address the following question: given a multi-to-one wireless sensor network in physical space, what is the optimal routing strategy to enable the energy-efficiency of the network with regard to a given mission and a certain amount of initial energy. We have focused on energy consumption involving data generation, data fusion and data transmission. We model the wireless sensor network as an undirected graph and put that energy efficient routing problem into a constrained optimization problem. In order to solve the optimal routing, we introduce the Ant Colony Optimization Algorithm, which is relatively easier than other algorithms to implement in a distributed environment because of its distributed computing and positive feedback features. Then we prove the convergence of the algorithm. Finally, in the simulation experiments, we show that the routes derived from out algorithm yield noticeably energy efficiency. Our optimization strategy can be applied to other distributed networks.

A systematic algorithm for fingerprint image quality assessment

The fingerprint image quality is a key factor on the match results since it will cause spurious and missed minutiae when matching with the low quality images. It is important to estimate the image quality to guide the feature extraction and matching. In this paper we investigate the specifications that can reflect the image quality such as orientation coherence, core position and so on. We define a quasi core as a stable point to examine the validity of the captured position. We apply the idea of penalty function in the optimization theory to combine the specifications to get a quality score. The method is robust since it investigates the quality specifications entirely. The testing results on FVC database are given to verify the feasibility and effectiveness.

An Optimal Cross-Layer Model for Maximum Lifetime Routing in Wireless Sensor Networks

In this paper, we firstly propose a maximum lifetime routing: the path cumulative power consumption routing(PCPC), based on the information of the two layers: medium access and routing. Secondly, a min-max optimal programming model is presented to describe the routing strategy. It aims to maximize the sensor network lifetime with minimal network power consumption by exploiting the cross-layer optimization. By solving this model, the number of transmitted packets of each relay node can be estimated precisely and it is the foundation of maximize sensor network lifetime. Detailed analytical and numerical results are given to verify the feasibility and efficiency of our programming model.