Dynamic similarity kernel for visual recognition

被引：0

作者：

Yan, Wang ^{[1
]}

Liu, Qingshan ^{[1
]}

Lu, Hanqing ^{[1
]}

Ma, Songde ^{[1
]}

机构：

[1] Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100080, Peoples R China

来源：

KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 2, PROCEEDINGS | 2006年 / 4252卷

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：

Inspired by studies of cognitive psychology, we proposed a new dynamic similarity kernel for visual recognition. This kernel has great consistency with human visual similarity judgement by incorporating the perceptual distance function. Moreover, this kernel can be seen as an extension of Gaussian kernel, and therefore can deal with non-linear variations well like the traditional kernels. Experimental results on natural image classification and face recognition show its superior performance compared to other kernels.

引用

页码：47 / 54

页数：8

共 28 条

[1] AIZERMAN MA, 1965, AUTOMAT REM CONTR+, V25, P821
[2] [Anonymous], 1999, NEURAL NETWORKS SIGN
[3] Generalized discriminant analysis using a kernel approach
Baudat, G
Anouar, FE
[J]. NEURAL COMPUTATION, 2000, 12 (10) : 2385 - 2404
[4] BELKIN M, 2001, ADV NEURAL INFORM PR, V13
[5] Chen YX, 2004, J MACH LEARN RES, V5, P913
[6] DESELAERS T, 2004, P 26 DAGM S PATT REC
[7] Duda R.O., 2001, Pattern Classification, V2nd
[8] The use of multiple measurements in taxonomic problems
Fisher, RA
[J]. ANNALS OF EUGENICS, 1936, 7 : 179 - 188
[9] SIMILARITY, INTERACTIVE ACTIVATION, AND MAPPING
GOLDSTONE, RL
[J]. JOURNAL OF EXPERIMENTAL PSYCHOLOGY-LEARNING MEMORY AND COGNITION, 1994, 20 (01) : 3 - 27
[10] GRAUMAN K, 2005, P INT C COMP VIS

← 1 2 3 →