VXL is a set of portable C++ libraries designed for computer vision research and implementation. Numerics, imaging, and geometry are provided by stand-alone core libraries, with easy to use APIs and sophisticated processing algorithms. Other libraries provide stereo, video, structure from motion, probability modeling, GUI design, classification, robust estimation, feature tracking, topology, 3d imaging, and much more. It is written and used by an international team from academia and industry.
Boosting is a meta-learning approach that aims at combining an ensemble of weak classifiers to form a strong classifier. Adaptive Boosting (Adaboost) implements this idea as a greedy search for a linear combination of classifiers by overweighting the examples that are misclassified by each classifier. icsiboost implements Adaboost over stumps (one-level decision trees) on discrete and continuous attributes (words and real values). This approach is one of the most efficient and simple to combine continuous and nominal values. This implementation is aimed at allowing training from millions of examples by hundreds of features in a reasonable amount of time/memory.
Algraeph is a tool for manual alignment of linguistic graphs, such as phrase structure trees or dependency structures, where each node corresponds to a subsequence of the analyzed input sentence. It allows you to express the similarity between two graphs by aligning their nodes and attaching relation labels to these alignments. Graphs are read from one or more graphbanks (or treebanks) in the GraphML or Alpino formats. Alignment relations are user-defined and are stored in a simple XML format, which can be used for further processing. The resulting parallel graph corpus is a useful data set for many tasks in computational linguistics and natural language processing.
libkdtree++ is a C++ template container implementation of k-dimensional space sorting, using a kd-tree. It sports a theoretically unlimited number of dimensions, and can store any data structure. Provided the data structure, it provides operator[0 - k-1] to access the individual dimensional components (arrays, std::vector already do) and a std::less implementation for the type of dimensional components. It has support for custom allocators, implements iterators, and provides standard find as well as range queries. It has amortised O(lg n) time (O(n lg n) worst case) on most operations (insert/erase/find optimised) and worst-case O(n) space, and also provides a means to rebalance and thus optimise the tree.
IkeWiki is a new kind of Wiki (a so-called "Semantic Wiki") developed by Salzburg Research that allows users to collaboratively annotate pages and links between pages with semantic annotations. Such annotations are useful because they give machines a certain amount of "understanding" of the content that goes beyond merely displaying the page. This information can then, for example, be used for context-specific presentation of pages, advanced querying, consistency verification, or drawing conclusions.
Bayesian Spam Filter is a class that can be used to detect spam in text messages using Bayesian techniques. It analyzes the text in terms of n-grams in a way that is idiom independent. It can be trained to progressively distinguish what is spam and what is not spam by detecting patterns in training samples. Training data is stored in a MySQL database.