计算机工程与应用2011，Vol.47Issue(1)：179-181,200,4.DOI:10.3778/j.issn.1002-8331.2011.01.050
偏最小二乘改进算法与特征抽取
Improved partial least squares and feature extraction.Computer Engineering and Applications,2011,47(1): 179-181.
摘要
Abstract
Non-iterative PLS based on orthogonal constraints(ONIPLS) can extract PLS features rapidly and effectively,while the features maybe correlative. PLS based on Uncorrelated Score Constraints(UCSNIPLS) can extract uncorrelated fcatures which make image recognition more effectively and steadily.2DPLS can extract features from image matrices, which can solve the small sample problems at the same time.While the classical class label encoding is too simple, fuzzy k-near neighbors' method is employed in order to make use of the sample distributions. Then improved algorithms of PLS and 2DPLS based on sample class label encoding are given. The results of experiments on ORL face database show that the improved algorithms presented are better than classical PLS,and can extract discriminant features efficiently.关键词
统计不相关/偏最小二乘/类标编码/特征抽取/人脸识别Key words
uneorrelated scores/ Partial Least Squares(PLS)/ class label encoding/ feature extraction/ face recognition分类
信息技术与安全科学引用本文复制引用
杨茂龙,王远方,孙权森,夏德深..偏最小二乘改进算法与特征抽取[J].计算机工程与应用,2011,47(1):179-181,200,4.基金项目
国家自然科学基金(the National Natural Science Foundation of China under Grant No.60773172) （the National Natural Science Foundation of China under Grant No.60773172）
江苏省自然科学基金(the Natural Science Foundation of Jiangsu Province of China under Grant No.BK2008411). （the Natural Science Foundation of Jiangsu Province of China under Grant No.BK2008411）
