Skip to main content

A hyperspectral imaging tools box

Project description

PySptools is a python module that implements spectral and hyperspectral algorithms. Specializations of the library are the endmembers extraction, unmixing process, supervised classification, target detection, noise reduction, convex hull removal, features extraction at spectrum level and a scikit-learn bridge. Version 0.15.0 introduce an experimental machine learning functionality based on XGBoost and LightGBM.

The library is designed to be easy to use and almost all functionality has a plot function to save you time with the data analysis process. The actual sources of the algorithms are the Matlab Hyperspectral Toolbox of Isaac Gerg, the pwctools of M. A. Little, the Endmember Induction Algorithms toolbox (EIA), the HySime Matlab module by José Bioucas-Dias and José Nascimento and science papers.

Functionalities

The functions and classes are organized by topics:

  • abundance maps: FCLS, NNLS, UCLS
  • classification: AbundanceClassification, NormXCorr, SAM, SID
  • detection: ACE, CEM, GLRT, MatchedFilter, OSP
  • distance: chebychev, NormXCorr, SAM, SID
  • endmembers extraction: ATGP, FIPPI, NFINDR, PPI
  • machine learning: XGBoost, LightGBM
  • material count: HfcVd, HySime
  • noise: Savitzky Golay, MNF, whiten
  • sigproc: bilateral
  • scikit learn: HyperEstimatorCrossVal, HyperSVC, HyperGradientBoostingClassifier, HyperRandomForestClassifier, HyperKNeighborsClassifier, HyperLogisticRegression and others
  • spectro: convex hull quotient, features extraction (tetracorder style), USGS06 lib interface
  • util: load_ENVI_file, load_ENVI_spec_lib, corr, cov, plot_linear_stretch, display_linear_stretch, convert2D, convert3D, normalize, InputValidation, ROIs and others

The library do an extensive use of the numpy numeric library and can achieve good speed for some functions. The library is mature enough and is very usable even if the development is at a beta stage (and some at alpha).

Installation

For installation, I refer you to the web site https://pysptools.sourceforge.io/installation.html

Dependencies

  • Python 2.7 or 3.5, 3.6
  • numpy, required
  • scipy, required
  • scikit-learn, required, version >= 0.18
  • spectral, required, version >= 0.17
  • matplotlib, required, [note: pytsptools >= 0.14.2 now execute on matplotlib 2.0.x and stay back compatible]
  • CVXOPT, optional, version >= 1.1.7, [note: to run FCLS]
  • jupyter, optional, version >= 1.0.0, [note: if you want to use the notebook display functionality]
  • tabulate, optional, [note: use by ml module]
  • pandas, optional, [note: use by ml module]
  • plotnine, optional, [note: use by ml module, a ggplot2]
  • lightgbm, optional, version 2.1.2 ONLY, [note: use by ml module]
  • xgboost, optional, version 0.72.1 ONLY, [note: use by ml module]

PySptools version 0.15.0 is developed on the linux platform with anaconda version 5.1.0 for both python 2.7 and 3.6.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for pysptools, version 0.15.0
Filename, size File type Python version Upload date Hashes
Filename, size pysptools-0.15.0.tar.gz (8.1 MB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring DigiCert DigiCert EV certificate Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page