Wavelet Toolbox
Wavelet Toolbox provides tools for time-frequency analysis of signals and multiscale image analysis, enabling data denoising, compression, and the detection of anomalies, change-points, and transients. It supports automated feature extraction using scattering transforms, continuous wavelet transforms (scalograms), Wigner-Ville distribution, and empirical mode decomposition. The toolbox also extracts edges and oriented features from images with wavelet, wavelet packet, and shearlet transforms.
Interactive apps allow users to perform signal denoising, time-frequency analysis, and image processing, with the ability to generate MATLAB scripts for reproducibility and automation. Additionally, you can generate C/C++ and CUDA® code for embedded deployment, facilitating real-time system integration.
Machine Learning and Deep Learning with Wavelets
Derive low-variance features from time series and image data for classification and regression with machine learning and deep learning models. Use continuous wavelet analysis to create 2D time-frequency maps from time series data, which can serve as inputs to deep convolutional neural networks (CNN).
Time-Frequency Analysis
Analyze signals in time and frequency, and images in space, spatial frequency, and angle with the continuous wavelet transform (CWT). Use the Time-Frequency Analyzer app to visualize scalograms of real and complex signals. Perform adaptive time-frequency analysis using nonstationary Gabor frames with the constant-Q transform (CQT).
Discrete Multiresolution Analysis
Use the decimated discrete wavelet transform (DWT) to analyze signals, images, and 3D volumes in finer octave bands. Implement nondecimated wavelet transforms and decompose nonlinear or nonstationary processes into intrinsic modes using empirical mode decomposition (EMD).
Filter Banks
Use dual-tree filter banks to improve directional selectivity in images. Design custom filter banks with the lifting method, offering a computationally efficient way to analyze signals and images at multiple resolutions or scales.
Denoising and Compression
Use wavelet and wavelet packet denoising to preserve features. The Wavelet Signal Denoiser app helps visualize and denoise 1D signals. Compress signals and images while maintaining perceptual quality.
Acceleration and Deployment
Accelerate your code by utilizing GPU and multicore processors for supported functions. Use MATLAB Coder to generate standalone, ANSI-compliant C/C++ code from Wavelet Toolbox functions that support code generation. Additionally, generate optimized CUDA code for running on NVIDIA® GPUs for supported functions.
