libperceptronnetwork is a library that models a multilayer feedforward perceptron network, a well-known and understood type of neural network. It can be used for a large number of recognition and categorization tasks. Besides providing the standard propagation and backpropagation algorithms, the library also provides variations to the backpropagation algorithm, such as optional weight-decay, momentum-term and optimal-tolerance methods. It comes with a handy programmers reference manual and two examples.
libGMUVision is framework for realtime computer vision applications that is designed to allow easier access to Firewire IIDC digital video cameras. It provides a set of C++ bindings for libdc1394 and Qt widgets for building graphical applications that process video streams in real time. A small sample application (Koriander Lite, based on the Coriander project) is included.
myBeasties is a highly flexible evolutionary programming module. It is designed to be extendable and customisable for maximum use by the Perl developer. Many species of genotypes can be evolved, and these can be used to build phenotypes of any size or complexity. These can be as simple as a list or as large as a whole class of objects.
DEVS has been developed for over a year to serve as an experimental framework for natural systems modeling techniques. It enables discrete event, general purpose, object oriented, component based, GIS connected, and collaborative visual simulation model development and execution. The sample model implementation shows that this experimental environment can be used for solving any complex problems solvable by discrete-event simulation, but it is especially suited for natural system simulation. Currently only hierarchical block and cellular models are modeled and simulated, but a multi-layered modeling paradigm for spatially distributed systems (with vector and cellular models) will eventually be implemented in the environment.
The Pattern Recognition Application Programmer's Interface aims to be a fully-featured, easy-to-use general C++ framework for various pattern recognition tasks, especially image analysis. It features support for many image formats, well-known image analysis methods, classification and feature analysis tools, XML serialization, etc.