Object class recognition and localization using sparse features with limited receptive fields

被引:255
作者
Mutch, Jim [1 ]
Lowe, David G. [2 ]
机构
[1] MIT, Dept Brain & Cognit Sci, Cambridge, MA 02139 USA
[2] Univ British Columbia, Dept Comp Sci, Vancouver, BC V6T 1W5, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
object class recognition; ventral visual pathway; sparsity; localized features;
D O I
10.1007/s11263-007-0118-0
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We investigate the role of sparsity and localized features in a biologically-inspired model of visual object classification. As in the model of Serre, Wolf, and Poggio, we first apply Gabor filters at all positions and scales; feature complexity and position/scale invariance are then built up by alternating template matching and max pooling operations. We refine the approach in several biologically plausible ways. Sparsity is increased by constraining the number of feature inputs, lateral inhibition, and feature selection. We also demonstrate the value of retaining some position and scale information above the intermediate feature level. Our final model is competitive with current computer vision algorithms on several standard datasets, including the Caltech 101 object categories and the UIUC car localization task. The results further the case for biologically-motivated approaches to object classification.
引用
收藏
页码:45 / 57
页数:13
相关论文
共 35 条
[1]   Learning to detect objects in images via a sparse, part-based representation [J].
Agarwal, S ;
Awan, A ;
Roth, D .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2004, 26 (11) :1475-1490
[2]  
[Anonymous], ICCV
[3]  
[Anonymous], 2001, COMPUTATIONAL NEUROS
[4]  
[Anonymous], CVPR
[5]  
[Anonymous], 2004, 2004 C COMP VIS PATT
[6]  
[Anonymous], 2005, CVPR
[7]  
[Anonymous], 2004, ECCV WORKSH STAT LEA
[8]  
[Anonymous], 2003, CVPR
[9]  
[Anonymous], 2005, CVPR
[10]  
CSURKA G, 2005, ECCV INT WORKSH STAT