Hierarchical feature extraction and object recognition based on biologically inspired filters

Pankaj Mishra; B. Keith Jenkins

doi:10.1117/12.839112

28 January 2010 Hierarchical feature extraction and object recognition based on biologically inspired filters

Pankaj Mishra, B. Keith Jenkins

Proceedings Volume 7538, Image Processing: Machine Vision Applications III; 75380S (2010) https://doi.org/10.1117/12.839112
Event: IS&T/SPIE Electronic Imaging, 2010, San Jose, California, United States

Abstract

A key to solving the multiclass object recognition problem is to extract a set of features which accurately and uniquely capture the salient characteristics of different objects. In this work we modify a hierarchical model of the visual cortex that is based on the HMAX model. The first layer of the HMAX model convolves the image with a set of multi-scale, multi-oriented and localized filters, which in our case are learnt from thousands of image patches randomly extracted from natural stimuli. These filters emerge as a result of optimization based in part on approximate-L1-norm sparseness maximization. A key difference between these filters and standard Gabor filters used in the HAMX model is that these filters are adapted to natural stimuli, and hence are more biologically plausible. Based on the modified model we extract a flexible set of features which are largely scale, translation and rotation invariant. This model is applied to extract features from Caltech-5 and Caltech-101 datasets, which are then fed to a support vector machine classifier for the object recognition task. The overall performance successfully demonstrates the plausibility of using filters learned from natural stimuli for feature extraction in object recognition problems.

Citation Download Citation

Pankaj Mishra and B. Keith Jenkins "Hierarchical feature extraction and object recognition based on biologically inspired filters", Proc. SPIE 7538, Image Processing: Machine Vision Applications III, 75380S (28 January 2010); https://doi.org/10.1117/12.839112

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available