Acknowledgment

1
The MATLAB Hyperspectral Image Analysis Toolbox
Samuel Rosario-Torres, samuel.rosario_at_ece.uprm.ed
u Dr. Miguel Velez-Reyes, mvelez_at_ece.uprm.edu Cent
er for Subsurface Sensing and Imaging Systems,
Tropical Center for Earth and Space Studies
University of Puerto Rico at Mayagüez, P. O. Box
9042, Mayagüez, Puerto Rico 00681.
What is the Hyperspectral Image Analysis
Toolbox? The Hyperspectral Image Analysis Toolbox
(HIAT) is a collection of functions that extend
the capability of the MATLAB numeric computing
environment. It has been implemented for the
Macintosh and PC-Windows systems using MATLAB. It
is intended for the analysis of multispectral and
hyperspectral images taken from the different
multispectral and hyperspectral sensors available
today. The purpose of this toolbox is the
development of a system that applies algorithms
developed from research done in the Laboratory
for Applied Remote Sensing and Image Processing
(LARSIP) at the University of Puerto Rico,
Mayagüez Campus.
Processing Example Image acquired from Hyperion,
a hyperspectral imager with 220 spectral bands
(.4 to 2.5 µm) at 10 nm spectral resolution and a
30m spatial resolution. The area covers the area
of Parguera in Lajas, Puerto Rico. This image has
been collected to study the application of
hyperspectral remote sensing to study the reefs
and other coastal characteristics of the area. In
this example, a subset of the data of 169x255
pixels and 196 bands is used.
Post-Processing Algorithms
Classification Map
MATLAB HIAT Version 1.4
ECHO Post-Classification Map
Toolbox Utilities
What Can You Do with HIAT?
Class Statistics
Pixels Spectral Signature
Loading Images Loading Images Loading Images
Matlab (.mat) JPEG and Matlab (.mat) JPEG and Remote Sensing (.bip, .bil, .bsq) TIFF
Image Enhancement Image Enhancement Image Enhancement
Resolution Enhancement Resolution Enhancement PCA Filter Enhancement
Feature Extraction/Selection Algorithms Feature Extraction/Selection Algorithms Feature Extraction/Selection Algorithms
Principal Components Analysis Singular Value Decomposition Band Subset Selection Information Divergence Band Subset Selection Discriminant Analysis Information Divergence Projection Pursuit Optimized Information Divergence Projection Pursuit Discriminant Analysis Information Divergence Projection Pursuit Optimized Information Divergence Projection Pursuit
Classifiers Classifiers Classifiers
Euclidean Distance Fishers Linear Discriminant Angle Detection Euclidean Distance Fishers Linear Discriminant Angle Detection Mahalanobis Distance Maximum Likelihood
Abundance Estimation Abundance Estimation Abundance Estimation
Non Negative Sum To One Non Negative Sum Less or Equal to One Non Negative Least Square Non Negative Sum To One Non Negative Sum Less or Equal to One Non Negative Least Square Unconstrained Positive Constrained
Post-Processing Algorithms Post-Processing Algorithms Post-Processing Algorithms
ECHO 2x2 ECHO 4x4 ECHO 2x2 ECHO 4x4 ECHO 3x3
Online Documentation Help Online Documentation Help Online Documentation Help
Online Help Documentation

• Download the Toolbox
• Go to www.censsis.neu.edu
• Click in Software link
• Click in SSI Toolboxes
• Click under The Hyperspectral Toolbox
• Or Go To http//www.censsis.neu.edu/software/hyper
  spectral/Hyperspectoolbox.html

CenSSIS VALUE ADDED
The Hyperspectral Image Analysis Toolbox will
provide support for CenSSIS Academic Institutions
interested in HSI. This is specifically for the
R3 thrust of CenSSIS, providing for the S2 and S4
areas this type of data analysis. Its
contribution extents into providing
infrastructure support for the development and
distribution processes and to develop guidelines
and procedures for software development and
testing.

• Acknowledgment
• Partially supported by the NSF Engineering
  Research Centers Program under grant ECC-9986821.
• Some algorithms development work was supported
  by
• NASA University Research Centers Program under
  grant NCC5-518
• Department of Defense under DEPSCoR Grant
  DAAG55-98-1-0016
• NIMA grant NMA2110112014.