计算机应用与软件
計算機應用與軟件
계산궤응용여연건
COMPUTER APPLICATIONS AND SOFTWARE
2014年
10期
189-191,196
,共4页
人脸识别%特征提取%局部保持投影%Fisher准则%多流形判别分析
人臉識彆%特徵提取%跼部保持投影%Fisher準則%多流形判彆分析
인검식별%특정제취%국부보지투영%Fisher준칙%다류형판별분석
Face recognition%Feature extraction%Locality preserving projection%Fisher criterion%Multi-manifold discriminant analysis
局部保持投影LPP（Locality Preserving Projection）是一种有效的非线性降维方法，能够使投影降维后的数据与原输入空间中的相似局部结构保持一致，但是该方法没有充分利用类间样本点的权重等重要信息。为了解决这个问题，提出基于Fisher准则的多流形判别分析FMMDA（Fisher Multi-Manifold Discriminant Analysis）方法。结合Fisher准则训练样本类内拉普拉斯图和样本均值类间拉普拉斯图，既保持了原样本的相似局部结构，又充分地利用了不同类别之间的权重。在ORL及Yale人脸库上验证了该方法的有效性。与其他几种最先进的方法相比，FMMDA方法取得了更好的识别效果。
跼部保持投影LPP（Locality Preserving Projection）是一種有效的非線性降維方法，能夠使投影降維後的數據與原輸入空間中的相似跼部結構保持一緻，但是該方法沒有充分利用類間樣本點的權重等重要信息。為瞭解決這箇問題，提齣基于Fisher準則的多流形判彆分析FMMDA（Fisher Multi-Manifold Discriminant Analysis）方法。結閤Fisher準則訓練樣本類內拉普拉斯圖和樣本均值類間拉普拉斯圖，既保持瞭原樣本的相似跼部結構，又充分地利用瞭不同類彆之間的權重。在ORL及Yale人臉庫上驗證瞭該方法的有效性。與其他幾種最先進的方法相比，FMMDA方法取得瞭更好的識彆效果。
국부보지투영LPP（Locality Preserving Projection）시일충유효적비선성강유방법，능구사투영강유후적수거여원수입공간중적상사국부결구보지일치，단시해방법몰유충분이용류간양본점적권중등중요신식。위료해결저개문제，제출기우Fisher준칙적다류형판별분석FMMDA（Fisher Multi-Manifold Discriminant Analysis）방법。결합Fisher준칙훈련양본류내랍보랍사도화양본균치류간랍보랍사도，기보지료원양본적상사국부결구，우충분지이용료불동유별지간적권중。재ORL급Yale인검고상험증료해방법적유효성。여기타궤충최선진적방법상비，FMMDA방법취득료경호적식별효과。
Locality preserving projection (LPP)is an effective nonlinear dimensionality reduction method which could preserve the similar local structure of the dimensionality-reduced data after projection in accord with that in original input space.However,it fails to take full advantage of the important information of the weights of between-class sample points.In order to address this issue,a new multi-manifold discriminant analysis method based on Fisher criterion is proposed,which combines the within-class Laplacian graph of training samples and the between-class Laplacian graph of sample average in Fisher criterion,while preserving the similar local structure of original sample,it also brings the weights between different classes into full play.The effectiveness of the method has been validated on ORL and Yale face database. Comparing with other state-of-the-art methods,the proposed FMMDA method achieves better recognition effect.
