Age estimation using a hierarchical classifier based on global and local facial features

The research related to age estimation using face images has become increasingly important, due to the fact it has a variety of potentially useful applications. An age estimation system is generally composed of aging feature extraction and feature classification; both of which are important in order to improve the performance. For the aging feature extraction, the hybrid features, which are a combination of global and local features, have received a great deal of attention, because this method can compensate for defects found in individual global and local features. As for feature classification, the hierarchical classifier, which is composed of an age group classification (e.g. the class of less than 20 years old, the class of 20-39 years old, etc.) and a detailed age estimation (e.g. 17, 23 years old, etc.), provide a much better performance than other methods. However, both the hybrid features and hierarchical classifier methods have only been studied independently and no research combining them has yet been conducted in the previous works. Consequently, we propose a new age estimation method using a hierarchical classifier method based on both global and local facial features. Our research is novel in the following three ways, compared to the previous works. Firstly, age estimation accuracy is greatly improved through a combination of the proposed hybrid features and the hierarchical classifier. Secondly, new local feature extraction methods are proposed in order to improve the performance of the hybrid features. The wrinkle feature is extracted using a set of region specific Gabor filters, each of which is designed based on the regional direction of the wrinkles, and the skin feature is extracted using a local binary pattern (LBP), capable of extracting the detailed textures of skin. Thirdly, the improved hierarchical classifier is based on a support vector machine (SVM) and a support vector regression (SVR). To reduce the error propagation of the hierarchical classifier, each age group classifier is designed so that the age range to be estimated is overlapped by consideration of false acceptance error (FAE) and false rejection error (FRE) of each classifier. The experimental results showed that the performance of the proposed method was superior to that of the previous methods when using the BERC, PAL and FG-Net aging databases.     

基于高斯混合模型和AdaBoost的夜间车辆检测

针对夜间车辆检测精度相对不高的问题，提出通过构建车头灯对空间几何关系的高斯混合模型（GMM）和采用逆投影车辆样本的AdaBoost分类器准确检测夜间车辆的方法。首先，在交通场景中根据车头灯对的空间位置关系设置逆投影面，通过图像预处理粗定位车灯区域；其次，在逆投影图像下利用车头灯对的空间几何关系构建车灯对的高斯混合模型，初步匹配车头灯对；最后，采用逆投影车辆样本，利用AdaBoost分类器进一步准确检测车辆。实验在3个交通场景的检测结果表明，与原始图像下的AdaBoost方法相比，所提方法的检测率提高了1.93%，漏检率降低了17.83%，误检率降低了27.61%；与D-S （Dempster-Shafer）证据理论方法相比，检测率提高了2.03%，漏检率降低了7.58%，误检率降低了47.51%。所提方法提高了相对检测精度，减少了地面反光和影子等的干扰，满足交通场景中夜间车辆检测的可靠性和准确性的要求。     

Investigation and simulation of a cross-flow air classifier

Extensive experimental tests and a computational study of the performance in a cross-flow air classifier have been carried out. A computational fluid dynamics (CFD) package—Fluent—is used to first understand and explain why the cuts or the sharpness of cut of this classifier are not as sharp as they ought to be, and then to optimize the geometry and operational conditions.

Flow fields of the classifier under various set-up conditions and geometry were measured by using laser Doppler anemometry (LDA). Using sieve analyses and the HELOS-laser method, the patterns of behaviour of separation parameters such as cut size and sharpness of cut have been investigated at different boundary conditions.

Using the Fluent package, a two-dimensional computational fluid dynamics model has been developed. The model is based on the Euler–Lagrangian approach. Different turbulence models have been tested. Both Fluent 4.5, with a structured grid, and Fluent 5.1, with structured and unstructured grids, have been used.

Discussions and analyses of the experimental, as well as the computational results, are presented. The simulation with a structured grid shows good agreement with experimental data, except for the sharpness of cut. The reasons of poor performance of the classifier have been found. The geometry is optimized and other conditions were also improved. The performance of the classifier is improved. The experimental observations together with the computed results should increase the depth of understanding of the underlying mechanisms.     

A NEW DIGITAL MODULATION RECOGNITION METHOD USING FEATURES EXTRACTED FROM GAR MODEL PARAMETERS

Based on the features extracted from generalized autoregressive (GAR) model parameters of the received waveform, and the use of multilayer perceptron(MLP) neural network classifier, a new digital modulation recognition method is proposed in this paper. Because of the better noise suppression ability of the GAR model and the powerful pattern classification capacity of the MLP neural network classifier, the new method can significantly improve the recognition performance in lower SNR with better robustness. To assess the performance of the new method, computer simulations are also performed.     

基于高维空间典型样本Steiner最小树覆盖模型的一类分类算法

最小生成树数据描述方法在刻画高维空间样本点分布时,将所有图形的边作为新增虚拟样本以提供同类样本分布描述,这种描述存在分支多覆盖模型复杂,且局部覆盖不够合理的问题。针对该问题,依据特征空间中同类样本分布的连续性规律,提出基于高维空间典型样本Steiner最小树覆盖模型的一类分类算法,该算法首先对目标类训练集进行样本修剪,去除冗余信息和噪声信息,选择最具代表性的样本作为训练集,然后对保留的典型样本构建Steiner最小树覆盖模型。算法分析和仿真实验结果表明,相比最小生成树数据描述,文中提出的方法能在较低覆盖模型复杂度的前提下更合理的描述目标类样本空间分布,构建更合理的覆盖模型,在分类正确率和适用样本规模上都表现出一定的优越性。      

几何集成的改进——特征边界点快速计算

针对优化几何集成方法(optimized geometric ensembles, OGE)在计算特征边界点集合的过程中包含大量冗余运算且效率较低的缺陷,分别利用Gabriel近邻规则及其启发式搜索法加速特征边界点的选取过程,提出了两种改进的几何集成方法--Gabriel OGE和启发式OGE,并与OGE进行比较实验。实验结果表明,虽然Gabriel OGE中计算特征边界点的时间复杂度与OGE一样,但是因为减少了大量数学运算,计算速度明显提高;而启发式OGE不仅将平均时间复杂度降低为O(dM²),而且在处理大数据集时,计算效率最高。Gabriel OGE和启发式OGE在保证分类结果的同时有效提高了特征边界点集合的计算速度,大幅度减少时间消耗。     

贝叶斯分类器的关联向量机多模型软测量建模

为了改善软测量模型的估计精度,提出了一种基于贝叶斯分类算法和关联向量机的多模型软测量建模方法。采用贝叶斯分类器对样本数据集进行分类,并对不同类别的输入数据分别建立关联向量回归机子模型,用“切换开关”方式组合作为最终的软测量模型输出。将该方法应用于双酚A生产过程的质量指标软测量建模,仿真结果表明：与单模型支持向量机相比,该方法估计精度较高,具有一定的应用价值。     

一种基于快速特征选择的故障诊断方法

针对故障诊断中数据存在噪声和高维的缺点,使用一种快速特征提取方法对故障数据进行降维,该方法以特征信号的均值和方差作为其权重衡量的依据。利用支持向量机的模式分类功能,构造了基于特征提取的多故障分类器。实例表明,在保证诊断效果的情况下,该方法实现了数据降维,降低了运算复杂度。     

一种基于新特征的车牌检测方法

车牌检测是车牌识别的关键所在,两种新的区域统计学特征能迅速排除大量的非车牌区域,在此基础上,采用增加了辅助判决的级联分类器来改进AdaBoost算法。实验表明,该算法与基于颜色特征分类器和传统的级联AdaBoost分类器相比,具有较快的检测速度、较高的检测率和较低的误检率。     

基于局部非负稀疏编码的掌纹识别方法

为了更有效地提取出图像的局部特征,在传统的非负稀疏编码(Hoyer-NNSC)算法的基础上,提出了一种新的具有稀疏度约束的局部NNSC (LNNSC)算法。该算法考虑了特征基向量的稀疏度约束和特征的最大化代表性,能够得到强化的图像局部特征;同时利用拉普拉斯密度模型作为特征系数的稀疏惩罚函数,保证了图像结构的稀疏性。在特征提取的基础上,进一步利用径向基概率神经网络(RBPNN)分类器,实现了掌纹的自动识别。仿真实验结果表明,与基于非负矩阵分解(NMF)、局部非负矩阵分解(LNMF)和Hoyer-NNSC的掌纹识别方法相比,该算法在掌纹识别研究中有较高的可行性和实用性。