Hyperspectral imaging is a technology used to identify objects by analyzing their spectral signatures. The goal of this project is to examine the effects of spatial and spectral compression on classification of hyperspectral cubes. A software package was developed to generate synthetic hyperspectral cubes in order to isolate the effect of spatial and spectral compression. It is shown that there is a certain amount of compression that can be applied before important information is lost and classification is rendered inaccurate.

• This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator

• Rao, Vinayak
• San Antonio, Geoffrey Stephen
• Vemis, Gregory William

Publisher

• Worcester Polytechnic Institute

Identifier

• 03D025M

Advisor

• Orr, John A.
• Ciaraldi, Michael J.

Year

• 2003

Center

• MIT Lincoln Laboratory-Lexington, Massachusetts Project Center - MQP

Sponsor

• MIT Lincoln Laboratory

Date created

• 2003-01-01

Resource type

• Major Qualifying Project

Major

• Computer Science
• Electrical Engineering

Rights statement

• In Copyright