Sparse Representation and Dictionary Learning as Feature Extraction in Vessel Imagery

Abstract

This report describes experiments designed to evaluate the usefulness of a specific algorithm for classifying images of commercial ships by class. This algorithm uses a technique known as sparse coding to represent images for classification. The sparse coding algorithm is compared with another algorithm evaluated in previous publications. RESULTS The sparse coding algorithm is shown to perform approximately as well as the algorithm it is compared with and does not appear to offer any improvement. RECOMMENDATIONS Additional research is required to identify algorithms best suited for the ship classification task. iii v 16. SECURITY CLASSIFICATION OF: a. REPORT b. ABSTRACT c. THIS PAGE 17. LIMITATION OF ABSTRACT 18. NUMBER OF PAGES 19a. NAME OF RESPONSIBLE PERSON 19B. TELEPHONE NUMBER (Include area code) Standard Form 298 (Rev. 8/98) Prescribed by ANSI Std. Z39.18