Multitask joint spatial pyramid matching using sparse representation with dynamic coefficients for object recognition

Mohammad-Hossein Hajigholam; Abolghasem-Asadollah Raie; Karim Faez

doi:10.1117/1.JEI.25.2.023019

12 April 2016 Multitask joint spatial pyramid matching using sparse representation with dynamic coefficients for object recognition

Mohammad-Hossein Hajigholam, Abolghasem-Asadollah Raie, Karim Faez

Author Affiliations +

Journal of Electronic Imaging, Vol. 25, Issue 2, 023019 (April 2016). https://doi.org/10.1117/1.JEI.25.2.023019

Abstract

Object recognition is considered a necessary part in many computer vision applications. Recently, sparse coding methods, based on representing a sparse feature from an image, show remarkable results on several object recognition benchmarks, but the precision obtained by these methods is not yet sufficient. Such a problem arises where there are few training images available. As such, using multiple features and multitask dictionaries appears to be crucial to achieving better results. We use multitask joint sparse representation, using dynamic coefficients to connect these sparse features. In other words, we calculate the importance of each feature for each class separately. This causes the features to be used efficiently and appropriately for each class. Thus, we use variance of features and particle swarm optimization algorithms to obtain these dynamic coefficients. Experimental results of our work on Caltech-101 and Caltech-256 databases show more accuracy compared with state-of-the art ones on the same databases.

Citation Download Citation

Mohammad-Hossein Hajigholam, Abolghasem-Asadollah Raie, and Karim Faez "Multitask joint spatial pyramid matching using sparse representation with dynamic coefficients for object recognition," Journal of Electronic Imaging 25(2), 023019 (12 April 2016). https://doi.org/10.1117/1.JEI.25.2.023019

Published: 12 April 2016

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