基于小波变换的X射线焊缝图像缺陷识别方法研究

经过长时间的研究发现,在焊缝图像缺陷识别中,传统的方法具有正确识别率低的问题,为此提出了基于小波变换的图像缺陷识别方法。输入获取的X射线焊缝初始图像信息,从帧数叠加、数字形态学变换和图像增强三个方面对初始图像进行预处理,约束小波变换阈值降低图像噪声,最后通过边缘检测,提取焊缝图像当中的缺陷特征。在对比实验当中,设立两种传统识别方法作为实验的对照组,提出的X射线焊缝图像缺陷识别方法为实验组,同时对统一型号的焊接工件进行缺陷识别,实验发现提出的识别方法的正确识别率高达91.8%。     

人耳识别技术研究进展综述

人耳识别是一种新的生物特征识别技术,目前,研究尚处于起步阶段,有关的理论和方法还很不完善。文章首先介绍了人耳自动系统的构成,然后分析了现有的各种人耳识别技术,最后提出了展望。     

An interior-point sequential approximate optimization methodology

The use of optimization in a simulation-based design environment has become a common trend in industry today. Computer simulation tools are commonplace in many engineering disciplines, providing the designers with tools to evaluate a designs performance without building a physical prototype. This has triggered the development of optimization techniques suitable for dealing with such simulations. One of these approaches is known as sequential approximate optimization. In sequential approximate minimization a sequence of optimizations are performed over local response surface approximations of the system. This paper details the development of an interior-point approach for trust-region-managed sequential approximate optimization. The interior-point approach will ensure that approximate feasibility is maintained throughout the optimization process. This facilitates the delivery of a usable design at each iteration when subject to reduced design cycle time constraints. In order to deal with infeasible starting points, homotopy methods are used to relax constraints and push designs toward feasibility. Results of application studies are presented, illustrating the applicability of the proposed algorithm.     

基于动态粒子群优化信息熵的人脸识别方法

人脸识别研究的目标主要有两个,一是提高识别正确率,二是降低训练与识别时间.信息熵等方法主要取决于参数选择,然而传统的优化算法难以解决此问题.粒子群算法等智能搜索技术可在较少的时间内给出问题的近似解.动态粒子群优化算法是在经典的微粒群算法的基础上所提出的一种高效的收敛性、稳定性的进化算法.采用动态粒子群算法对信息熵优化寻找最优参数,并结合特征提取方法,用于人脸图像的识别中,为人脸识别问题的研究开辟了新的途径.最后通过仿真实验得出结论表明,既减少了计算复杂度,降低训练与识别时间,又保证实时性,提高识别正确率,得到了理想的结果.     

Adaptive augmented Lagrangian methods: algorithms and practical numerical experience

In this paper, we consider augmented Lagrangian (AL) algorithms for solving large-scale nonlinear optimization problems that execute adaptive strategies for updating the penalty parameter. Our work is motivated by the recently proposed adaptive AL trust region method by Curtis et al. [An adaptive augmented Lagrangian method for large-scale constrained optimization, Math. Program. 152 (2015), pp. 201–245.]. The first focal point of this paper is a new variant of the approach that employs a line search rather than a trust region strategy, where a critical algorithmic feature for the line search strategy is the use of convexified piecewise quadratic models of the AL function for computing the search directions. We prove global convergence guarantees for our line search algorithm that are on par with those for the previously proposed trust region method. A second focal point of this paper is the practical performance of the line search and trust region algorithm variants in Matlab software, as well as that of an adaptive penalty parameter updating strategy incorporated into the Lancelot software. We test these methods on problems from the CUTEst and COPS collections, as well as on challenging test problems related to optimal power flow. Our numerical experience suggests that the adaptive algorithms outperform traditional AL methods in terms of efficiency and reliability. As with traditional AL algorithms, the adaptive methods are matrix-free and thus represent a viable option for solving large-scale problems.     

结合改进Surf特征的素描人脸识别

素描人脸识别属于异质人脸识别范畴,是刑侦领域的研究热点。根据素描人脸识别的特点,对已配准的人脸图像进行伪素描转化,并用Surf算法提取伪素描图像对的特征点。对经过提取后的伪素描特征点进行坐标邻域一致性优化,排除坐标邻域相对位置不一致的特征点,最后统计伪素描图像对的有效特征点,以实现识别的目的。利用现有的素描人脸库,进行实验验证,在选取50个特征点时的识别率达到99%,验证了算法的有效性。该算法经优化后,可用于素描人脸识别。     

细菌趋药性算法理论及应用研究进展

细菌趋药性算法是优化领域一种新的仿生进化算法。该算法利用细菌在引诱剂环境下的应激反应动作来进行函数优化。针对细菌趋药性算法,首先介绍了其基本原理;然后讨论了近年来对该方法的若干改进;最后详述了细菌趋药性算法未来的研究方向和主要研究内容,该方法是具有实际研究价值的函数优化算法。     

动态二进制翻译中热路径优化的软件实现

在动态二进制翻译中，热路径的识别和生成是提高二进制翻译器效率的重要环节。为了提高热路径预测的命中率，必须在程序的运行中搜集较为详细的信息，这必然增加系统的开销。因此，在准确率和开销之间做出权衡十分必要。该文在研究现有热路径算法的基础上，提出了一种改进的基于路径的热路径识别和优化算法，并对结果进行了分析。     

Synthesis of Mechanisms Using Time-Varying Dimensions

Many methods of performing mechanism synthesis rely on an attempt to redefine the dimensions of the system in such a way that a deviation from the desired behavior is minimized by the use of optimization methods. During the optimization process the optimizer may, however, suggest values of the dimensions, or design variables, that lead to infeasible designs, i.e. dimensions for which the mechanism cannot be assembled in one or more positions.With the method proposed her, this problem is overcome by allowing the dimensions to vary during the motion of the system and subsequently minimizing the deviation of each variable dimension over a cycle. That is, for each time step the dimensions are allowed to change in order to obtain assembly as well as a desired kinematic behavior. This will lead to a variation of each dimension during a cycle of the mechanism, and this variation is the objective that is sought minimized. The minimization problem is solved using the optimality criterion.     

支持向量机算法实现人民币序列号识别

人民币序列号识别是一个小样本、非线性和高维模式识别问题,是当前模式识别中的难题之一,具有重要研究意义和实用价值。主要研究了统计学习理论中支持向量机的二次优化算法,并将支持向量机应用于货币序列号的机器识别中。将次序最小优化算法构建的支持向量机用于序列号识别,充分发挥了支持向量机解决小样本、非线性和高维模式识别问题的优点。支持向量机（SVM）实验结果表明,这种支持向量机货币识别方法具有较高的可实现性和识别精度。     

基于多目标优化多任务学习的端到端车牌识别方法

本文针对多个车牌识别任务之间存在竞争和冲突,导致难以同时提高多个车牌的识别率的问题,提出基于多目标优化多任务学习的端到端车牌识别方法.首先,通过分析某些车牌识别任务容易占主导地位,而其他任务无法得到充分优化的问题,建立基于多任务学习的车牌识别模型.接着,针对字符分割造成车牌识别准确率较低、鲁棒性较差的问题,提出基于多任务学习的端到端车牌识别方法.最后,针对多个车牌识别任务间难以权衡的问题,提出一种基于多目标优化的多任务学习方法,以提高多个车牌识别的准确率.将本文所提方法在标准车牌数据集上进行测试,实验结果验证了该方法的有效性和优越性,其他代表性方法相比可以提高车牌识别的准确率、快速性和鲁棒性.     

An interval algorithm for multi-objective optimization

This paper presents an interval algorithm for solving multi-objective optimization problems. Similar to other interval optimization techniques, [see Hansen and Walster (2004)], the interval algorithm presented here is guaranteed to capture all solutions, namely all points on the Pareto front. This algorithm is a hybrid method consisting of local gradient-based and global direct comparison components. A series of example problems covering convex, nonconvex, and multimodal Pareto fronts is used to demonstrate the method.     

基于PSO神经网络的故障诊断方法研究

将粒子群优化算法和BP算法相结合,提出了一种基于粒子群神经网络的故障诊断方法.该方法分阶段实施神经网络的训练,有效地加强了算法的全局搜索能力,采用PSO优化了传播中的权值、阈值以及网络结构.这不仅弥补了BP算法的不足,而且删除了冗余连接,提高了故障模式识别的能力.仿真结果表明该方法加快了神经网络的学习收敛速度,提高了故障模式的识别正确率,可以有效地应用于设备的故障诊断.     

新型LeNet-FC卷积神经网络模型算法的研究

针对已有的卷积神经网络（Convolutional Neural Network，CNN）在人脸识别训练中出现过拟合、收敛速度慢以及识别准确率不高的问题，提出了新型的LeNet-FC卷积神经网络模型。通过增加网络层、缩小卷积核等结构改进以及采用优化的对数-修正线性单元（Logarithmic Rectified Linear Unit，L_ReLU）激活函数，该模型在人脸识别训练的准确率达到了99.85%。同时基于LeNet-FC卷积神经网络模型设计了一个人脸识别系统。该系统在ORL人脸库的仿真测试实验中识别准确率达到了96%。     

团队进步算法在快速响应码识别中的应用

针对QR码在采集过程中易发生寻像图形受污染的情况,首先改进了QR码的识别模式模型,接着将团队进步算法用于QR码基元识别,该算法通过将优化变量分成普通组和精英组,经过学习、探索等运算,合理地更新成员,最终可搜寻得到最优解,将QR码从图像中提取出来。实验证明,该方法简单有效,可用于拓宽QR码的使用范围。     

一种新的基于特征选择的虹膜识别方法

为了提高虹膜识别的准确率,提出了一种新的基于特征选择的虹膜识别方法。在虹膜的定位上采用了弹性模板的方法,对虹膜图像进行有效定位。针对虹膜图像的纹理分布特点,采用了多尺度Gabor滤波器对虹膜的不同纹理区域进行有针对性的特征提取;然后利用遗传算法和粒子群优化算法进行特征选择,去除特征向量中的冗余信息;最后利用SVM分类模型进行虹膜的识别。为了检验方法的有效性,在CASIA虹膜数据库上进行验证,实验结果表明该方法具有较高的识别精准度。     

基于ABC-SVM的考生行为自动识别

针对支持向量机在考生行为自动识别中的参数优化问题,提出了一种人工蜂群算法优化支持向量机的考生行为自动识别方法。首先将支持向量机参数编码成为人工蜂群的蜜源,以考生行为识别正确率作为搜索目标,然后通过人工蜂群之间的信息交流和共享找到支持向量机的最优参数,并建立最优考生行为识别模型,最后采用仿真实验测试已建立考生行为识别模型的性能。实验结果表明,本文方法不仅提高了考生行为识别的正确率,而且加快了考生行为识别的速度,可以很好的满足考生行为自动识别实时性要求。     

An entropy based method for extracting robust binary-templates

In applications based on template matching, the design of the template is a critical point and has a considerable effect on the overall performance that can be obtained. In this paper we present a method, applicable to binary images, for extracting robust templates. Starting from a provisional prototype (defined as the image that minimizes its overall distance from the samples of a training set), the template is obtained by eliminating unreliable pixels determined by means of an entropy-based criterion. The method is compared experimentally with the matched filtering technique in the recognition of symbols on topographic maps and shows promising results regarding the recognition rate and the computational cost of the matching process.