孙明月1,
葛为民1, 2,,
1.天津理工大学天津市先进机电系统设计与智能控制重点实验室 ??天津 ??300384
2.天津理工大学机电工程国家级实验教学示范中心 ??天津 ??300384
基金项目:国家重点研发计划(2017YFB1303304)，天津市科技计划重大专项(17ZXZNGX00110)，天津市自然科学重点基金(16JCZDJC30400)
详细信息
作者简介:王肖锋：男，1977年生，博士，讲师，研究方向为发育机器人和机器学习
孙明月：女，1994年生，硕士生，研究方向为机器人智能学习
葛为民：男，1968年生，博士，教授，研究方向为机器人智能控制
通讯作者:葛为民 geweimin@tjut.edu.cn
中图分类号:TP391.41计量
文章访问数:1977
HTML全文浏览量:685
PDF下载量:48
被引次数:0
出版历程
收稿日期:2018-12-10
修回日期:2019-05-06
网络出版日期:2019-05-22
刊出日期:2019-11-01
An Incremental Feature Extraction Method without Estimating Image Covariance Matrix
Xiaofeng WANG1, 2,Mingyue SUN1,
Weimin GE1, 2,,
1. Tianjin Key Laboratory for Advanced Mechatronical System Design and Intelligent Control, Tianjin University of Technology, Tianjin 300384, China
2. National Experimental Teaching Demonstration Center of Electromechanical Engineering, Tianjin University of Technology, Tianjin 300384, China
Funds:The National Key R & D Plan of China (2017YFB1303304), The Tianjin Science and Technology Planed Key Project (17ZXZNGX00110), The Tianjin Natural Science Key Foundation (16JCZDJC30400)
摘要
摘要:针对2维主成分分析(2DPCA)算法无法实现在线特征提取及无法体现完整数据结构信息等问题，该文提出一种基于图像协方差无关的增量式2DPCA(I2DPCA)算法。该算法无需对图像协方差矩阵进行特征值分解奇异值分解，复杂度将大为降低，提高了特征提取速度。针对I2DPCA仅提取了横向特征的问题，又提出一种增量式行列顺序2DPCA(IRC2DPCA)算法，该算法对I2DPCA的特征矩阵再次进行纵向特征提取，保留了图像的横向与纵向结构信息，实现了行列两个方向上的特征提取与数据降维。最后，以自建的物块数据集、通用的ORL和Yale人脸数据集分别进行对比实验，结果表明，该文算法在收敛率、分类率及复杂度等性能方面均得到了显著提高，其收敛率达到99%以上，分类率可达97.6%，平均处理速度为29 帧/s，能够满足增量特征提取的实时处理需求。
关键词:模式识别/
协方差无关/
特征提取/
增量学习/
2维主成分分析
Abstract:To solve the problems that Two-Dimensional Principal Component Analysis (2DPCA) can not implement the on-line feature extraction and can not represent the complete structure information, an Incremental 2DPCA (I2DPCA) without estimating covariance matrices is presented by an iterative estimation method, not to deal with the image covariance matrices by the eigenvalue decomposition or the singular value decomposition. The complexity will be greatly reduced and the on-line feature extraction speed can be improved. The proposed I2DPCA can only extract the horizontal features, and thus another Incremental Row-Column 2DPCA (IRC2DPCA) is proposed to incrementally extract the longitudinal ones from the feature matrices of the I2DPCA. The IRC2DPCA can preserve the horizontal and longitudinal features and implement the dimensionality reduction in both row and column directions. Finally, a series of experiments are carried out with the self-built block dataset, ORL and Yale face datasets, respectively. The results show that the proposed algorithms have significantly improved the performances of the convergence rate, the classification rate and the complexity. The convergence rate is over 99%, the classification rate can reach 97.6% and the average processing speed is about 29 frames per second, and it can meet the on-line feature extraction requirements for incremental learning.
Key words:Pattern recognition/
Covariance-free/
Feature extraction/
Incremental learning/
Two-Dimensional Principal Component Analysis (2DPCA)
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=c05450f4-556a-4379-b848-325cb97f6380
