The Bob Project¶
Bob is a free signal-processing and machine learning toolbox originally developed by the Biometrics group at Idiap Research Institute, Switzerland. The toolbox is written in a mix of Python and C++ and is designed to be both efficient and reduce development time.
- To learn about this project’s motivations and history, visit Motivations and Philosophy.
- For a brief summary of what you can do with Bob, have a look at Overview.
- To just get started using Bob, skip ahead to Installing Bob.
- If you make use of Bob or any Satellite Packages, we would appreciate if you cited one of our publications as described in Overview.
- For more detailed information, scroll down to the User’s Guide, Developer’s Guide or Reference manual.
We believe in free software and development standards. Bob is a freely available library, licensed under the terms of the GPL v3. For more information on licensing, please visit our Licensing Terms.
Enjoy!
Overview¶
Installation¶
User’s Guide¶
- Introduction
- Multi-dimensional Arrays
- Input/Output
- Image and signal processing
- Audio processing
- Machines
- Trainers
- Principal component analysis
- Linear discriminant analysis
- Neural networks: multi-layer perceptrons (MLP)
- Support vector machines
- K-means
- Maximum likelihood for Gaussian mixture model
- MAP-adaptation for Gaussian mixture model
- Joint Factor Analysis
- Inter-Session Variability
- Total Variability (i-vectors)
- Whitening
- Within-Class Covariance Normalisation
- Probabilistic Linear Discriminant Analysis (PLDA)
- Database
- Performance Evaluation
- A Complete Application: Analysis of the Fisher Iris Dataset
- Organize Your Work in Satellite Packages
- Bug Reporting and Feature Requesting
