纹理豪斯多夫距离在人脸识别算法中的应用

很多经典的人脸识别方法难以适应姿势变化及人脸错位的情形。为了解决这一问题,提出一种基于纹理豪斯多夫距离(THD)的人脸识别算法。将人脸图像的空间量及纹理特征相结合,使其在深入的头部转动和人脸错位中都有很高的容错度。在FERET及Yale两大人脸数据库的实验表明,与其他经典的方法相比较,所提出的方法取得了更好的识别效果。     

基于差分相关的星载AIS信号帧同步

在星载AIS接收机中,船舶信号在传输过程中产生的大范围时延和多普勒频移,给正确解码带来了困难。针对这一问题,基于AIS帧结构特点,提出一种差分相关帧同步算法。算法中将AIS帧结构中训练序列、开始标志和结束标志设计为间隔式特征序列作为同步码,通过差分相关函数来实现帧同步。仿真实验结果表明,该算法有较好的抗频偏特性,且在低信噪比下,性能要优于差分卷积法。     

硅压阻式气压高度计的设计与实现

采用硅压阻式压力传感器,以ATmega88PA为控制器设计了气压高度计。内嵌全温度范围的曲面拟合算法进行温度补偿及线性化处理,解决了压力传感器的温漂和非线性问题,并用海拔高度与气压的关系计算高度。测量结果通过RS-485接口发送给上位机。测试结果表明,该气压高度计压力测量误差优于0.50‰,分辨率为0.01 h Pa,线性度为0.999 9;标准大气环境下高度测量误差为0.16 m,线性度为0.999 8。该气压高度计具有质量小、功耗低、精度高、工作可靠等优点。     

浅析呼和浩特市大气SO2发展趋势及防治对策

本文通过对二氧化硫的形成及危害的阐述，以及对我市近几年大气中二氧化硫监测结果的分析，针对发展趋势和存在的问题，根据实际情况提出相应的建议。     

Morphologies and microstructures of tree-like carbon produced at different reaction conditions in a CVD process

Centimeter-size multi-branched tree-like carbon structures have been generated by the catalytic chemical vapor deposition of toluene using ferrocene as the catalyst precursor and investigated by means of SEM, TEM, and EDX. It is found that a temperature of 1000-1200 °C and a carrier gas flow rate of 1000-2500 ml/min are necessary for the generation of the carbon trees. Their morphologies and microstructures change greatly with the changing reaction conditions. The fractal dimensions of the trees are calculated to quantitatively investigate the influence of different reaction temperatures on the morphologies.     

Stability analysis and controller design of interval type-2 fuzzy systems with time delay

The type-2 fuzzy models can handle the system uncertainties directly based on the type-2 fuzzy sets. In this paper, the Takagi–Sugeno fuzzy model approach is extended to the stability analysis and controller design for interval type-2 (IT2) fuzzy systems with time-varying delay. Delay-dependent robust stability criteria are developed in terms of linear matrix inequalities by using the improvement technique of free-weighting matrices. Less conservative results are obtained by considering the information contained in the footprint of uncertainty. Finally, two simulation examples are presented to illustrate the effectiveness of the theoretical results. One is provided to show the merits of the proposed method, the other based on the continuous stirred tank reactor model is given to illustrate the design processes of IT2 fuzzy controller for a nonlinear system with parameter uncertainties.     

Electrochemical micromachining of nitinol by confined-etchant-layer technique

The confined etchant layer technique has been applied to fabricate complex three-dimensional microstructures on nitinol for the first time. HF and HNO₃ were locally and simultaneously electrogenerated at the mold surface to etch a nitinol workpiece. NaOH was used as an efficient scavenger to confine the etchant close to the mold. Cyclic voltammetry was employed to study the electrochemical behavior of a Pt electrode in the etching solution in order to choose an appropriate potential for etchant generation on the mold. The thickness of the confined etchant layer was estimated to be several micrometers by inspecting the deviation of the sizes of the etched spots from the sizes of those on the microelectrode. Thus, the composition of the electrolyte could be optimized for better etching precision. By optimizing the composition of the electrolyte, complex microstructures on a Pt-Ir mold bearing the logo “XMU” of Xiamen University were successfully fabricated on nitinol. The etched patterns were approximately negative copies of the mold, and the precision of duplication could easily reach the micrometer scale.     

A Rough RBF Neural Network Based on Weighted Regularized Extreme Learning Machine

Adjusting parameters iteratively is a traditional way of training neural networks, and the Rough RBF Neural Networks (R-RBF-NN) follows the same idea. However, this idea has many disadvantages, for instance, the training accuracy and generalization accuracy etc. So how to change this condition is a hot topic in Academics. On the basis of Extreme Learning Machine (ELM), this paper proposes a Weighted Regularized Extreme Learning Machine (WRELM), taking into account both minimizing structured risk and weighted least-squares principle, to train R-RBF-NN. The traditional iterative training method is replaced by the minimal norm least-squares solution of general linear system. The method proposed in this paper, increasing controllability of the entire learning process and considering the structured risk and empirical risk, can improve the performance of learning and generalization. Experiments show that it can reach a very superior performance in both time and accuracy when WRELM trains the Rough RBF Neural Networks in pattern classification and function regression, especially in pattern classification, which can improve the generalization accuracy more than 3.36 % compared with ELM. Obviously, the performance of the method proposed in this paper is better than the traditional methods.     

To accelerate shot boundary detection by reducing detection region and scope

Video Shot Boundary Detection (SBD) is the fundamental process towards video summarization and retrieval. A fast and efficient SBD algorithm is necessary for real-time video processing applications. Extensive work has focused on accurate shot boundary detection at the expense of demanding computational costs. In this paper, we propose a fast SBD approach that reduces the computation pixel-wise and frame-wise while still giving satisfactory accuracy. The proposed approach substantially speeds up the computation through reducing both detection region and scope. Color histogram and mutual information are used together to measure the difference between frames. Corner distribution of frames is utilized to exclude most of false boundaries. We conduct extensive experiments to evaluate the proposed approach, and the results show that our approach can not only speed up SBD, but also detect shot boundaries with high accuracy in both Cut (CUT) and Gradual Transition (GT) boundaries.