Weighted and robust incremental method for subspace learning

被引：0

作者：

Skocaj, D ^{[1
]}

Leonardis, A ^{[1
]}

机构：

[1] Univ Ljubljana, Fac Comp & Informat Sci, Ljubljana 61000, Slovenia

来源：

NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS I AND II, PROCEEDINGS | 2003年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Visual learning is expected to be a continuous and robust process, which treats input images and pixels selectively. In this paper we present a method for subspace learning, which takes these considerations into account. We present an incremental method, which sequentially updates the principal subspace considering weighted influence of individual images as well as individual pixels within an image. This approach is further extended to enable determination of consistencies in the input data and imputation of the values in inconsistent pixels using the previously acquired knowledge, resulting in a novel incremental, weighted and robust method for subspace learning.

引用

页码：1494 / 1501

页数：8

共 19 条

[1]

ANAES H, 2002, PAMI, V24, P1215

[2]

[Anonymous], 2 IEEE WORKSH APPL C

[3]

Artac M, 2002, INT C PATT RECOG, P781, DOI 10.1109/ICPR.2002.1048133

[4]

Brand M, 2002, LECT NOTES COMPUT SC, V2350, P707

[5] An eigenspace update algorithm for image analysis [J].

Chandrasekaran, S ;

Manjunath, BS ;

Wang, YF ;

Winkeler, J ;

Zhang, H .

GRAPHICAL MODELS AND IMAGE PROCESSING, 1997, 59 (05) :321-332

[6]

De la Torre F, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS, P362, DOI 10.1109/ICCV.2001.937541

[7] LOWER RANK APPROXIMATION OF MATRICES BY LEAST-SQUARES WITH ANY CHOICE OF WEIGHTS [J].

GABRIEL, KR ;

ZAMIR, S .

TECHNOMETRICS, 1979, 21 (04) :489-498

[8] Merging and splitting eigenspace models [J].

Hall, P ;

Marshall, D ;

Martin, R .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (09) :1042-1049

[9]

Hall P. M., 1998, BMVC 98. Proceedings of the Ninth British Machine Vision Conference, P286

[10] Robust recognition using eigenimages [J].

Leonardis, A ;

Bischof, H .

COMPUTER VISION AND IMAGE UNDERSTANDING, 2000, 78 (01) :99-118

← 1 2 →