改进的ISOMAP算法在人脸识别中的应用

计算机与现代化

改进的ISOMAP算法在人脸识别中的应用

1.金陵科技学院信息技术学院，江苏南京211169；2.河海大学计算机与信息学院，江苏南京210098

收稿日期:2015-04-16 出版日期:2015-09-21 发布日期:2015-09-24
作者简介: 郭海凤（1980-），女，山东枣庄人，金陵科技学院信息技术学院讲师，河海大学计算机与信息学院博士研究生，研究方向：信息检索，模式识别。
基金资助:
江苏省高校自然科学研究项目（14KJD520003）

Application of Improved ISOMAP Algorithm for Face Recognition

1. Institute of Information Technology, Jinling Institute of Technology, Nanjing 211169, China;

2. College of Computer and Information Engineering, Hohai University, Nanjing 210098, China

Received:2015-04-16 Online:2015-09-21 Published:2015-09-24

摘要/Abstract

摘要：

图像是一种高维数据，在图像检索中容易产生维数灾难问题。传统的降维方法很难有效地揭示高维数据的内在本质结构，而流形学习是一种非线性降维方法，其目的是获取高维观测数据的

低维嵌入表示并挖掘出隐藏在高维图像数据中的本征信息与内在规律。本文结合SIFT特征提取算法与ISOMAP流形学习算法在人脸图像数据集上进行检索实验。分析探讨近邻参数以及内在本征维数的大小

对人脸图像识别效果的问题。

关键词: 图像检索, 流形学习, 降维, 本征维数

Abstract:

Image data is high-dimensional data which make it easily prone to the dimension disaster. The traditional dimensionality reduction methods can not recover the

inherent structure. Manifold learning is a nonlinear dimensionality reduction technique, it aims to find low-dimensional compact representations of high-dimensional observation

data and explore the inherent law and intrinsic dimension of data. In this paper, the feature extraction method-SIFT and the adaptive ISOMAP method are combined and conducted on

the real face image dataset. This paper analyzes and discusses the problem of the effects of the neighborhood parameter and the intrinsic dimension size on the face image

recognition.

Key words: image retrieval, manifold learning, dimensionality reduction, intrinsic dimension

郭海凤1，2，陈月霞1，孙周宝2. 改进的ISOMAP算法在人脸识别中的应用[J]. 计算机与现代化.

GUO Hai-feng1,2, CHEN Yue-xia1, SUN Zhou-bao2. Application of Improved ISOMAP Algorithm for Face Recognition[J]. Computer and Modernization.

［1］ Jolliffe I. Principal Component Analysis ［M］. 2nd ed. New York: Springer Verlag, 2002. 
［2］ Comon Pierre. Independent component analysis:A new concept? ［J］. Signal Processing, 1994,36(3):287-314.
［3］ Cox T F, Cox M A A. Multidimensional Scaling［M］. 2nd ed. Chapman and Hall/CRC, 2000.
［4］ Tenenbaum J B, Silva V D, Langford J C. A global geometric framework for nonlinear dimensionality reduction［J］. Science, 2000,290(5500):2319-2323.
［5］ Tenenbaum J B. Mapping a manifold of perceptual observations［C］// Advances in Neural Information Processing Systems. 1998,10：682-688.
［6］ Wen Guihua, Jiang Lijun, Wen Jun. Kernel relative transformation with applications to enhancing locally linear embedding［C］// Proceedings of the International Joint

Conference on Neural Networks. 2008:3401-3406
［7］ Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding［J］. Science, 2001,2909(5500):2323-2326.
［8］ Wang Heyong, Zheng Jie, Yao Zhengan, et al. Improved locally linear embedding through new distance computing［C］// Advances in Neural Networks. 2006:1326-1333.
〖LL〗［9］ Chang H, Yeung D. Robust locally linear embedding［J］. Pattern Recognition, 2006,39(6):1053-1065.
［10］Valencia-Aguirre J, lvarez-Mesa A, Daza-Santacoloma G, et al. Automatic choice of the number of nearest neighbors in locally linear embedding［C］// Progress in

Pattern Recognition, Image Analysis, Computer Vision, and Applications. 2009:77-84.
［11］Eftekhari A, Abrishami-Moghaddam H, Babaie-Zadeh M. k/K-Nearest neighborhood criterion for improvement of locally linear embedding［C］// Computer Analysis of Images and

Patterns. 2009:808-815.
［12］Goldberg Y, Ritov Y. LDR-LLE: LLE with low-dimensional neighborhood representation［C］// Advances in Visual Computing. 2008:43-54.
［13］Zhang Shiqing. Enhanced supervised locally linear embedding［J］. Pattern Recognition Letters, 2009,30(13):1208-1218.
［14］Hou Chenqing, Zhang Changhui, Wu Yi, et al. Stable local dimensionality reduction approaches［J］. Pattern Recognition, 2009,42(9):2054-2066.
［15］Belkin M, Niyogi P. Laplacian eigenmaps for dimensionality reduction and data representation［J］. Neural Computation, 2003,15(6):1373-1396.
［16］Lowe D G. Object recognition from local scale-invariant features［C］// Proceeding of IEEE International Conference on Computer Vision. 1999,2:1150-1157.
［17］Lowe D G. Distinctive image features from scale-invariant keypoints［J］. International Journal of Computer Vision, 2004,60(2):91-110.

[1]	王欣怡, 尹四清, 洪军. 融合注意力机制的非对称深度监督哈希[J]. 计算机与现代化, 2023, 0(05): 26-31.
[2]	刘锟, 曾曦, 邱梓珩, 陈周国, . 基于RoBERTa-WWM 和HDBSCAN的文本聚类算法[J]. 计算机与现代化, 2022, 0(03): 48-52.
[3]	徐惠, 铁治欣, 舒莹. 基于特征匹配的快速降维排序搜索方法[J]. 计算机与现代化, 2022, 0(02): 85-91.
[4]	黄欣辰, 皋军, 黄豪杰. 基于PCA降维的成对约束半监督聚类集成[J]. 计算机与现代化, 2021, 0(01): 94-99.
[5]	周芳宇, 陈淑荣. 一种特征增强的Tri-CNN行人再识别方法[J]. 计算机与现代化, 2020, 0(09): 60-65.
[6]	黄建理,杜金燃,谢家全,秦科. 一种基于改进KNN的大数据离群点检测算法[J]. 计算机与现代化, 2017, 0(5): 67-70,75.
[7]	郭琳，翟社平，高山. 知识图谱中的语义推理算法[J]. 计算机与现代化, 2017, 0(12): 71-76.
[8]	韩丹丹，韩立新. 基于张量局部保持投影算法的图像检索[J]. 计算机与现代化, 2017, 0(1): 71-74.
[9]	胡晨1，江泽涛2. 一种SIFT像素点筛选预处理降维双向匹配方法[J]. 计算机与现代化, 2016, 0(9): 54-59+72.
[10]	刘会河，徐维超，刘舜. 基于SVM的降维方法在三类ROC分析中的应用[J]. 计算机与现代化, 2016, 251(07): 49-54.
[11]	朱凌云1,朱征宇1,2,齐新勇1. 融合多种内容特征的图像检索算法[J]. 计算机与现代化, 2015, 0(9): 17-21.
[12]	濮永仙. 基于图像内容检索的作物病害识别数据库系统研究[J]. 计算机与现代化, 2015, 0(4): 54-60.
[13]	陈秋平. 考虑视觉显著性的部分相似图像检索[J]. 计算机与现代化, 2015, 0(4): 82-85,89.
[14]	王梦蕾. 一种基于区域检测的图像检索相关反馈方法[J]. 计算机与现代化, 2015, 0(1): 75-80.
[15]	苏锦旗，张文宇. 基于模糊聚类的改进LLE算法[J]. 计算机与现代化, 2014, 0(5): 10-13.