|Table of Contents|

Locally Maintainning Projection of Typical Correlation Analysis(PDF)

《哈尔滨理工大学学报》[ISSN:1007-2683/CN:23-1404/N]

Issue:
2013年05期
Page:
65-69
Research Field:
计算机与控制工程
Publishing date:

Info

Title:
Locally Maintainning Projection of Typical Correlation Analysis
Author(s):
CHENG Wei- yue LIN Ke- zheng LIU Shuai LI Shu
School of Computer Science and Technology,Harbin University of Science and Technology
Keywords:
canonical component analysis algorithm locality preserving projections algorithm class informa-
tion
maximum correlation
PACS:
TP391. 4
DOI:
-
Abstract:
Abstract: According to the problem that conventional subspace linear analysis method can t describe the man-
ifold structure of the sample accurately,based on the theory of canonical component analysis algorithm and locality
preserving projections algorithm,we combine two kinds of algorithms. The article puts forward restricted- class lo-
cality preserving canonical component analysis algorithm. The algorithm distinguishes the sample information and
keeps the local information structure of the sample by introducing the class information. The algorithm achieves the
level of maximum related on the base of making a distinction of the sample class information. It as well as makes
the feature projections have no relativity. This algorithm significantly improves the algorithm s recognition rate. The
algorithm respectively does the experiment on the Yale face and AR face database. The recognition rate can reach to
98%.

References:

-

Memo

Memo:
-
Last Update: 2013-12-26