Bio-inspired invariant visual feature representation based on K-SVD and SURF algorithms

Authors:
Liying Jiang;Yanjiang Wang;Weifeng Liu
Affiliations:
China University of Petroleum (East China), Qingdao, P.R. China;China University of Petroleum (East China), Qingdao, P.R. China;China University of Petroleum (East China), Qingdao, P.R. China
Venue:
Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Year:
2013

Citing 8
Cited 0

Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories

CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 12 - Volume 12
Object Recognition with Features Inspired by Visual Cortex

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Multiclass Object Recognition with Sparse, Localized Features

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Robust Object Recognition with Cortex-Like Mechanisms

IEEE Transactions on Pattern Analysis and Machine Intelligence
Speeded-Up Robust Features (SURF)

Computer Vision and Image Understanding
Using Human Visual System modeling for bio-inspired low level image processing

Computer Vision and Image Understanding
-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation

IEEE Transactions on Signal Processing
Matching pursuits with time-frequency dictionaries

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a bio-inspired invariant visual feature representation method is proposed. A set of Gabor filters with different parameters and global max operation are performed to improve the adaptability to scale and shift changes. In order to extract rotation-invariant features of images, the K-SVD and SURF algorithms are introduced into the traditional HMAX model. Prototypes (feature templates) are learned by the K-SVD algorithm, while the SURF descriptor of patches aims to enhance the rotation invariance. Experimental results on image classification demonstrate the superiority of the proposed feature representation method.