Recent progress in fingerprint recognition

Fingerprint recognition has been increasingly used to realize personal identification in civilian's daily life, such as ID card, fingerprints hard disk and so on. Great improvement has been achieved in the on-line fingerprint sensing technology and automatic fingerprint recognition algorithms. Various fingerprint recognition techniques, including fingerprint acquisition, classification, enhancement and matching, are highly improved. This paper overviews recent advances in fingerprint recognition and summarizes the algorithm proposed for every step with special focuses on the enhancement of low-quality fingerprints and the matching of the distorted fingerprint images. Both issues are believed to be significant and challenging tasks. In addition, we also discuss the common evaluation for the fingerprint recognition algorithm of the Fingerprint Verification Competition 2004 (FVC2004) and the Fingerprint Vendor Technology Evaluation 2003 (FpVTE2003), based on which we could measure the performance of the recognition algorithm objectively and uniformly.     

Multi-Modal Systems Thinking and a Self-Study of Teaching Reform: Realizing the Ethical Mode of Being

I describe multi-modal systems thinking in the context of my qualitative investigation of the influence of open discourse on technicism in a University Business Computing Course. I discontinued the research on realizing, through a reflective self study, influenced by my reading of the multi-modal thinking of the Amsterdam School, that I had acted unethically. I thus changed my research and my teaching practice. I note that this approach has recently been incorporated into systems thinking in the work of J. R. D. de Raadt, whose university informatics teaching reform, informed by the "way of the prophet," resonates with my reforms.     

免疫算法与遗传算法比较

在介绍免疫算法与遗传算法概念的基础上，阐明了二的不同特点，并通过仿真实验表明了它们之间在功能和应用方面的区别。     

基于广义典型相关分析融合和鲁棒概率协同表示的人脸指纹多模态识别

针对单模态生物特征识别容易受自身条件和环境变化的影响,鉴于人脸识别和指纹识别已经在生物识别系统中得到了广泛应用,提出了二者特征信息融合的多模态生物特征识别方法。该方法首先对人脸、指纹图像进行预处理,并对这两种模态均提取LBP和Gabor特征,然后将广义典型相关分析方法分别引入到人脸多特征融合和指纹多特征融合中,应用分块对角矩阵组合上述融合的人脸特征和指纹特征,最后用鲁棒概率协同表示分类器进行分类。在两个多模态数据库上的实验结果表明:与人脸或指纹单模态生物特征识别相比,基于人脸指纹的多模态生物特征识别具有更高的识别率和更好的稳定性;所提出的基于广义典型相关分析的特征融合方法优于传统的融合方法。     

基于遗传算法的联合运输路径优化

联合运输是在能源危机、交通拥堵及环境污染约束下的一种理想运输模式。随着国际贸易的飞速发展,联合运输成为了一个热点问题。而联合运输的运输路径优化问题又是联合运输中的重点和难点之一。将综合运输的运输路径优化问题转化成为一个最短路径问题,以成本和时间为优化目标建立了选择最优路径的模型,并应用交叉、变异概率的自适应机制等实现技术设计了一个遗传算法作为求解算法对实例问题进行了求解验证,结果表明该算法具有良好的性能。     

Three-phase Pupil Localization Method in Non-ideal Eye Images

Pupil localization is a very important preprocessing step in many reel applications. Accurate and robust pupil localization in non-ideal eye images is a challenging task. A detailed method of pupil localization in non-ideal eye images is proposed. This method is implemented in three main phases： first, segment the rough pupil region based on Gaussian Mixture Model： then modify the rough segmentation result using morphological method to minimize the influence of some disturbing factors; last estimate the pupil parameters based on minimizing the least square error. The proposed method is first tested on CASIA iris image dataset, and then on our self-captured iris dataset which contains a wider variety of iris images. Experiments show that the proposed method can perform well for nonideal eye images of various qualities.     

基于人工免疫网络的多峰值函数优化

针对多峰值函数优化中常规方法难以同时搜索出多个极值的问题,借鉴生物免疫系统的相关机理,提出了基于人工免疫网络的多峰值函数优化算法,并在一些典型的测试函数上进行性能测试。实验结果表明,该算法具有很好的全局和局部搜索能力,能够较好地保持抗体的多样性,获得多峰值函数的全部或多个优化解。     

一种基于聚类分析的小生境微粒群优化算法

为了寻找多峰函数的多个极值点,在标准微粒群优化算法的基础上,提出一种基于聚类分析的小生境微粒群优化算法.采用基于密度的聚类分析方法辨识和构造小生境微粒子群,通过这种多子群方法,可以保持种群多样性,直接搜索到所有的局部/全局最优点.实验测试结果表明,该算法对一元函数优化和多元函数优化都有很好的效果.图6,参10.     

刚性拉索振动主动LQR和D-V-I Bang-Bang控制效果比较

由于某些情况下拉索的抗弯刚度对振动频率有一定的影响,文章在考虑拉索抗弯刚度的基础上,建立了刚性拉索振动主动控制模型;融合线性二次型最优控制(LQR)策略和传统的Bang-Bang单模态控制策略,提出了适用于刚性拉索振动主动多模态D-V-I Bang-Bang控制的简化模型;仿真分析表明,主动D-V-I Bang-Bang控制比LQR控制更适合应用于工程实际。     

虹膜识别研究综述

对国内外虹膜识别研究的现状进行了归纳, 对虹膜识别存在的问题进行了分析, 并讨论了未来的发展方向.