|
Multivariate Image Analysis (MIA) Toolbox
Version
1.0.6 of MIA_Toolbox is the current release... see
below for change notes.
Multivariate
Image Analysis (MIA) toolbox expands the already expansive
PLS_Toolbox
functionality by including many image-specific functions and
builds on PLS_Toolbox interfaces to make analysis of multivariate
images simple and intuitive.
With
MIA_Toolbox, multivariate images from microscopy to remote
sensing can be easily analyzed using the same PLS_Toolbox
tools you are already familiar with. MIA_Toolbox allows you
to load, manipulate, and analyze multivariate images in the
Analysis graphical interface as well as using many of the
higher-level command-line functions. Principal components
analysis, multivariate curve resolution (ALS and Purity),
SIMCA and PLSDA classification, K-Means clustering, and even
PLS or PCR regression can all be performed on images with
this extension pack. MIA_Toolbox also adds a number of functions
which
are designed to take advantage of the special "spatial"
relationship inherent in a multivariate image including functions
like Evolving Window Factor Analysis and Maximal Autocorrelative
Factors, and a suite of Texture functions.
MIA_Toolbox includes:
- "Automatic image
display" technology to recognize and automatically
present appropriate model results in image format.
- Image importing and building functions to
make assembly of multivariate images easier.
- Image specific functions including EWFA,
MAF, and an image-enhanced Cluster analysis.
- Texture-analysis functions which encode the
texture in an image into a vector for pattern or regression
analysis.
- Enables most standard
PLS_Toolbox functions to work with images.
Release
1.0.5 Now Available
MIA_Toolbox
is currently available in Version 1.0.5. This release delivers
a number of bug fixes and plotting enhancements along with
the use of images in the Purity analysis method.
[-] Hide Notes
The following are among the bug fixes and enhancements
in Version 1.0.5:
plotgui_plotimage
- force use of classcolors
function.
- adjust binning logic.
- rescale density plots based on maximum value observed.
- increase performance with reduced number of getappdata
calls.
- improve density mode precision.
- switch to normal scatter mode from density mode if <100
points.
- allow exclusion in n-way datasets.
- force title on when plotting "image of" something.
histcontrast
- keep on screen always.
- force closed if parent disappears.
camecard
- help and some IO changes.
camecaeval
- various logic improvements.
cluster_img
- added option to request that all clusters be no larger
than X% of data.
- renamed algorithm "classmean" to "kmeans".
Note: MIA 1.0.5 REQUIRES PLS_Toolbox Version 4.1!
[-] Hide Notes
You
can purchase a copy or get a demonstration license from our
License Manager.
NOTE:
MIA_Toolbox requires PLS_Toolbox Version 4.1 or later. You
must upgrade your PLS_Toolbox
to Release 4.1 to use MIA_Toolbox. See the
MIA_Toolbox Pricelist for other ordering information.
Product
Support
Eigenvector
Research offers user support for MIA_Toolbox by e-mail at
helpdesk@eigenvector.com. Questions
are almost always answered within 24 hours (and usually much
less). Updates and bug fixes will be available for users to
download from our web site. For information on other support
options, see our technical
support page.
System
Requirements
MIA_Toolbox
requires PLS_Toolbox version 4.1 or higher and MATLAB
6.5, 7.x or higher. MIA_Toolbox does not require other
MATLAB toolboxes. Like most MATLAB toolboxes, MIA_Toolbox
is platform independent. It will function on any platform
on which MATLAB functions (e.g. MAC, PC, Unix).
|