Sparse distributed localized gradient fused features of objects

TL;DR

This paper introduces a sparse, hierarchical feature encoding method that significantly improves object recognition accuracy and robustness across multiple datasets compared to existing methods.

Contribution

A novel sparse, localized gradient feature encoding approach that enhances object recognition performance and robustness, outperforming eight existing methods.

Findings

Achieved up to 93% accuracy on ALOI database

Improved recognition accuracy by 8-10% over existing methods

Demonstrated robustness to noise, scaling, and shifts

Abstract

The sparse, hierarchical, and modular processing of natural signals is related to the ability of humans to recognize objects with high accuracy. In this study, we report a sparse feature processing and encoding method, which improved the recognition performance of an automated object recognition system. Randomly distributed localized gradient enhanced features were selected before employing aggregate functions for representation, where we used a modular and hierarchical approach to detect the object features. These object features were combined with a minimum distance classifier, thereby obtaining object recognition system accuracies of 93% using the Amsterdam library of object images (ALOI) database, 92% using the Columbia object image library (COIL)-100 database, and 69% using the PASCAL visual object challenge 2007 database. The object recognition performance was shown to be robust to variations in noise, object scaling, and object shifts. Finally, a comparison with eight existing object recognition methods indicated that our new method improved the recognition accuracy by 10% with ALOI, 8% with the COIL-100 database, and 10% with the PASCAL visual object challenge 2007 database.