一种基于协作表示的判别局部保持投影方法  

A Collaborative Representation-based Method of Discriminant Locality Preserving Projections

作　　者：李实秋 LI Shi-qiu(Department of R&D Center,Nanjing Guodian Nanzi Rail Transit Engineering Co.,Ltd,Nanjing 210000,China)

机构地区：[1]南京国电南自轨道交通工程有限公司研发中心,江苏南京210000

出　　处：《计算机与现代化》2023年第6期43-47,共5页Computer and Modernization

基　　金：国家自然科学基金资助项目(61801363)。

摘　　要：判别局部保持投影(DLPP)算法是一种判别特征提取的方法,用于流形学习的典型降维算法,它能够利用判别信息,提取出最佳的判别特征,但是DLPP算法往往会忽略样本间的协作重构关系,从而导致算法识别率较低的问题。本文提出一种基于协作表示的判别局部保持投影(CRDLPP)方法。该方法首先利用协作表示方法对所有训练样本的协作重构误差进行计算,然后将该重构误差值作为正则项引入DLPP的目标函数中,最后通过求解新的目标优化问题得到最优投影矩阵。为了验证CRDLPP算法在图像识别方面的有效性,选取Yale人脸库和COIL20图像库进行算法仿真实验,结果表明,本文的CRDLPP算法在图像识别方面相比其他经典降维算法有着较高的识别率。Discriminant locality preserving projections(DLPP)is an effective discriminative feature extraction approach based on manifold learning.It is one of the typical representative algorithms of flow pattern dimensionality reduction.It can use the dis⁃criminant information to extract the best discriminant features.However,it fails to exploit the collaborative reconstruction rela⁃tionship between samples,and thus usually leads to a lower recognition rate.To cope with this problem,a collaborative represen⁃tation based discriminant locality preserving projections(CRDLPP)is proposed.CRDLPP first calculates the collaborative recon⁃struction errors of all the samples by collaborative representation mechanism,and then incorporates them as a regularization term into the objective function of DLPP.The optimal projection matrix is finally obtained by solving the new objective optimization problem.In order to verify the good performance of CRDLPP method in image recognition,this paper selects public image data⁃bases such as Yale and coil20 for experiments.The results show that the CRDLPP algorithm in this paper has a higher recognition rate than other classical data dimensionality reduction algorithms in image recognition.

关 键 词：判别局部保持投影 协作表示 协作重构误差 图像识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]