| Wavelet Toolbox Release Notes | |
New Features
This section summarizes the new features and enhancements introduced in the Wavelet Toolbox 3.0.
For information about Wavelet Toolbox features that are incorporated from Version 2.2, see New Features in the Wavelet Toolbox 2.2 Release Notes.
Wavelet Design for CWT
The New Wavelet for CWT tool designs a new wavelet adapted to a given pattern using least squares optimization. The new wavelet can be used for accurate pattern detection using the continuous wavelet transform (cwt). This new tool is useful for creating new wavelets for accurate 1-D pattern detection. From the command line, use the pat2cwav function.
Image Fusion
The Image Fusion tool performs fusion of two images. Image fusion using wavelets merges the wavelet decompositions of two original images using various fusion methods applied to approximations coefficients and details coefficients. Examples of uses of this tool are creating a new image from two different images and restoring an image from two fuzzy versions of an original image. From the command line, use the wfusimg and wfusmat functions to fuse two images and fuse two matrices or arrays, respectively.
Fractional Brownian Generation 1-D
The Fractional Brownian Generation 1-D tool performs the random generation of fractional Brownian motion, which is a useful model for Internet traffic and financial series. From the command line, use the wfbm and wfbmesti functions to synthesize and perform parameter estimation of fractional Brownian motion, respectively.
Lifting Methods
You can use lifting methods to design new wavelets. The new lifting methods also allow integer-to-integer wavelet transforms and transforms using different length decomposition high-pass and low-pass filters. Five groups of new lifting functions are included in the Wavelet Toolbox version 3.0:
addlift--Add primal or dual elementary lifting steps to a lifting scheme
displs--Display a lifting scheme
lsinfo--Information about lifting schemes
bswfun--Compute and plot biorthogonal "scaling and wavelet" functions
filt2ls--Transform a quadruplet of filters to a lifting scheme
liftfilt--Apply elementary lifting steps on quadruplet of filters
ls2filt--Transform a lifting scheme to a quadruplet of filters
liftwave--Provides lifting scheme associated to a wavelet
wave2lp--Provides Laurent polynomials associated to a wavelet
wavenames--Provides wavelet names available for LWT
lwt--1-D Lifting Wavelet Transform
lwt2--2-D Lifting Wavelet Transform
lwtcoef--Extract or reconstruct 1-D LWT wavelet coefficients
lwtcoef2--Extract or reconstruct 2-D LWT wavelet coefficients
ilwt--Inverse 1-D Lifting Wavelet Transform
ilwt2--Inverse 2-D Lifting Wavelet Transform
Speed Enhancements
Many functions, including those involving decomposition and reconstruction, have been enhanced so they run more efficiently.
New Extension Modes for DWT
Four new extension modes are available for dwt, which allows specifying half- or whole-point symmetry, or half- or whole-point anti-symmetry. See dwtmode. These new extension modes are supported by both wextend to extend or truncate signal or images, and by the corresponding GUI tools: Signal Extension and Image Extension.
New Supported Image Formats
Images stored using JPEG, TIFF, PCX, and others can be directly loaded into the Wavelet Toolbox GUI.
Images stored in uint8 format can be used in all the 2-D tools.
Images stored in True Colour mode are converted automatically in indexed mode when loaded in the 2-D tools. See the Wavelet Toolbox documentation on working with images for more information.
| | Wavelet Toolbox 3.0.1 Release Notes | Major Bug Fixes | |
© 1994-2005 The MathWorks, Inc.