Kernel propagation strategy: A novel out-of-sample propagation projection for subspace learning

Kernel matrix optimization (KMO) aims at learning appropriate kernel matrices by solving a certain optimization problem rather than using empirical kernel functions. Since KMO is difficult to compute out-of-sample projections for kernel subspace learning, we propose a kernel propagation strategy (KPS) based on data distribution similar principle to effectively extract out-of-sample low-dimensional features for subspace learning with KMO. With KPS, we further present an example algorithm, i.e., kernel propagation canonical correlation analysis (KPCCA), which naturally fuses semi-supervised kernel matrix learning and canonical correlation analysis by means of kernel propagation projections. In KPCCA, the extracted correlation features of out-of-sample data not only incorporate integral data distribution information but also supervised information. Extensive experimental results have demonstrated the superior performance of our proposed method.     

图像语义提取方法研究

为解决从图像的低层视觉特征到高层语义特征的＂语义鸿沟＂问题,对当前的语义提取方法进行研究,简单介绍了图像语义层次模型,并根据语义信息的来源不同,归纳总结了图像语义中基于处理范围的方法,基于机器学习的方法,基于人机交互的方法和基于外部信息源的提取方法,这些工作为图像语义提取和图像语义检索等研究提供有益参考。     

A self-adaptive weighted affinity propagation clustering for key frames extraction on human action recognition

In this paper, we propose a novel approach for key frames extraction on human action recognition from 3D video sequences. To represent human actions, an Energy Feature (EF), combining kinetic energy and potential energy, is extracted from 3D video sequences. A Self-adaptive Weighted Affinity Propagation (SWAP) algorithm is then proposed to extract the key frames. Finally, we employ SVM to recognize human actions on the EFs of selected key frames. The experiments show the information including whole action course can be effectively extracted by our method, and we obtain good recognition performance without losing classification accuracy. Moreover, the recognition speed is greatly improved.     

基于小波包分析特征参数的说话人识别系统

介绍了说话人识别系统,研究MFCC提取原理与小波包分析的基础上,提出了一种基于小波包分析的新型语音特征参数WPDC。在研究了WPDC提取算法的基础上,建立了一个神经网络模型的说话人识别系统,实验比较了MFCC与WPDC的识别性能,验证WPDC了具有很高的识别率,是一种很好的语音特征参数。     

基于QuickBird遥感影像的城市道路信息提取方法研究

从光谱提取和特征提取两个重要方面总结了目前城市道路信息提取的基本方法,讨论了这些方法的优缺点。根据昆明市QuickBird遥感影像的特点以及城市道路的特点,提出基于Sobel边缘检测算法提取城市道路的流程以及处理方法,对城市道路信息提取的方法进行研究和探索。     

基于多Agent技术的分布式信息抽取系统研究

讨论了信息抽取的必要性及其现状,并提出一个基于多Agent技术的分布式信息抽取系统模型.系统主要有信息抽取Agent、数据清洗Agent、数据保存Agent等以及相应的知识库组成.并采用分而治之的思想,把信息抽取中遇到的问题分解,分配到各个Agent去完成.提出一种新的规则表示方法,抽取规则可以根据网页结构进行调整,该系统具有一定的自适应性.     

Organic light-emitting diodes fabricated on recessed anodes for light extraction enhancement

Circular recesses have been fabricated on indium tin oxide (ITO) anodes to enhance light extraction of organic light-emitting diodes (OLEDs). The effects of recess depth and recess coverage ratio on the performance of a green OLED were systematically investigated. Results showed that the current efficiency could be enhanced from 40.7 cd/A of a planar device to 47.2 cd/A of the device with a recess depth of 100 nm and a recess coverage ratio of 14.1%. The enhanced light extraction by the recess wall effect was realized to be the major factor leading to the improved efficiency. The efficiency is however limited by the accompanying increase in electrical resistivity of the ITO films at deep recesses and high recess coverage ratios. Despite of the insignificant efficiency enhancement (up to 16%) in this study, this recessed ITO approach provides a simple architecture to enhance waveguide mode light extraction without adding an internal medium.     

Prism coupling method to evaluate the light extraction efficiency of outcoupling substrates

One of the key challenges in organic light-emitting diodes (OLEDs) for lighting applications is efficient light extraction from the planar, multi-layered OLED stack. Several different light extraction approaches are being explored currently by researchers, however characterizing light extraction films after fabricating OLEDs is not a viable approach when the outcoupling films have large surface roughness and is time consuming as well. Here we apply prism coupling method (PCM), a simple and elegant tool, to characterize outcoupling films. We show the effectiveness of PCM in estimating light extraction efficiency of outcoupling films. PCM can expedite selection and optimization of various light extraction approaches without the need to build OLEDs. The experimental results are corroborated by the optical simulations done using ray tracing method taking into account Mie scattering from wavelength sized spherical inclusions in an outcoupling film.     

基于特征点的影像匹配

在数字摄影测量中,影像匹配代替了传统的人工观测,来达到自动确定同名像点的目的。影像匹配的理论与实践,是实现自动立体量测的关键,也是数字摄影测量的重要研究课题之一。本文中对基于特征点的影像匹配思路及特征点的提取与匹配中所涉及到的各种算法进行说明,并通过实验对算法展开分析。