改進(jìn)的統(tǒng)計(jì)不相關(guān)最優(yōu)鑒別矢量集

吳小俊; 楊靜宇; 王士同; JosefKittler; 陸介平

改進(jìn)的統(tǒng)計(jì)不相關(guān)最優(yōu)鑒別矢量集

吳小俊^{①②③;楊靜宇},
楊靜宇,
王士同,
JosefKittler,
陸介平

計(jì)量
- 文章訪(fǎng)問(wèn)數(shù): 2465
- HTML全文瀏覽量: 118
- PDF下載量: 759
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2003-05-28
- 修回日期: 2004-03-09
- 刊出日期: 2005-01-19

An Improved Optimal Set of Statistical Uncorrelated Discriminant Vectors

摘要

摘要: 該文對(duì)統(tǒng)計(jì)不相關(guān)最優(yōu)鑒別矢量集算法進(jìn)行研究,在分析統(tǒng)計(jì)不相關(guān)最優(yōu)鑒別矢量集算法的基礎(chǔ)上提出了一種改進(jìn)的方法。該方法在類(lèi)內(nèi)散布矩陣的特征空間中求解統(tǒng)計(jì)不相關(guān)最優(yōu)鑒別矢量集。為了加快特征抽取速度,利用基于圖像鑒別分析的維數(shù)壓縮方法,對(duì)圖像數(shù)據(jù)進(jìn)行了壓縮。在ORL和Yale人臉數(shù)據(jù)庫(kù)的數(shù)值實(shí)驗(yàn),驗(yàn)證本文所提出的方法的有效性。
- 模式識(shí)別; 特征抽取; 鑒別分析; 最佳鑒別矢量集; 人臉識(shí)別
Abstract: This paper presents a research on the algorithm of optimal set of statistically uncorrelated discriminant vectors. An improved algorithm has been proposed on the basis of the analysis of the conventional algorithm of statistical uncorrelated discriminant vectors, which solves the optimal set of statistically uncorrelated discriminant vectors in the eigen space of the within-class scatter matrix Sw. The dimension of images has been reduced using the dimension reduction method based on image discriminant analysis in order to speed the process of feature extraction. The numerical experiments on facial databases of ORL and Yale show the effectiveness of the proposed method.

HTML全文

參考文獻(xiàn)(1)

Turk M, Pentland A. Eigenfaces for face recognition[J].J. Cognitive Neuroscience.1991, 3(1):71-[2]Foley D H, Sammon J W. An optimal set of discriminant vectors,IEEE Trans. on Computers, 1975, 24(3): 281 -289.[3]Duchene J, Leclercl S. An optimal transformation for discriminant and principal component analysis. IEEE Trans. on PAMI, 1988, 10(6): 978 - 983.[4]Kittler J. On the discriminant vector method of feature selection[J].IEEE Trans. on Computers.1977, 26(6):604-[5]Hong Z Q. Algebraic feature extraction of image for recognition[J].Pattern Recognition.1991, 24(3):211-[6]洪子泉,楊靜宇.用于圖像識(shí)別的圖像代數(shù)特征抽取.自動(dòng)化學(xué)報(bào),1992,18(2):232-238.[7]Cheng Y Q, Yang J Y, et al.. A novel feature extraction method for image recognition based on similar discriminant function[J].Pattern Recognition.1993, 26(1):115-[8]Liu K, Cheng Y Q,Yang J Y, et al.. Algebraic feature extraction for image recognition based on an optimal discriminant criterion[J].Pattern Recognition.1993, 26(6):903-[9]Liu K, Yang J Y, et al.. A generalized optimal set of diseriminant vectors[J].Pattern Recognition.1992, 25(7):731-[10]郭躍飛,楊靜宇.求解廣義最佳鑒別矢量的一種迭代算法及人臉識(shí)別.計(jì)算機(jī)學(xué)報(bào),2000,23(11):1189-1195.[11]郭躍飛.人臉圖像代數(shù)特征提取與最佳鑒別矢量的研究.[博士論文],南京:南京理工大學(xué),2000.[12]Guo Yue-Fei, Yang Jing-Yu, et al.. Feature extraction method based on the generalized fisher discriminant criterion and facial recognition[J].Pattern Analysis Application.2001, 4(1):61-[13]吳小俊, 楊靜宇, 王士同等. A new algorithm for solving optimal discriminant vectors. Journal of Computer Science and Technology, 2001, 3(17): 324 - 331.[14]金忠.人臉圖像特征抽取與維數(shù)研究.[博士論文],南京:南京理工大學(xué),1999.[15]金忠,楊靜宇.一種具有統(tǒng)計(jì)不相關(guān)性的最佳鑒別矢量集.計(jì)算機(jī)學(xué)報(bào),1999,22(10):1105-1108.[16]吳小俊.圖像特征抽取與識(shí)別理論及其在人臉識(shí)別中的應(yīng)用研究.[博士論文],南京:南京理工大學(xué),2002.[17]吳小俊,楊靜宇,王士同等.A new optimal set of uncorrelated discriminant vectors and its application. Proceedings of WCICA02 (IEEE 02EX527), Shanghai, China, 2002:340 - 344.[18]吳小俊,楊靜宇,王士同等.廣義DKL變換及其在人臉識(shí)別中的應(yīng)用研究.計(jì)算機(jī)科學(xué),2003,30(1):87-89.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪(fǎng)問(wèn)統(tǒng)計(jì)