Artificial Ingenuity - Theseus Word Recognition

Theseus Word Recognition System

The Theseus system is a proprietary fuzzy-logic based word recognition algorithm capable of recognizing words too jumbled for human recognition. This technology is based upon Artificial Ingenuity's theories of the method used when humans process words visually. This new technology was originally conceived in September of 2003, and has proven to be vastly superior to previous spell-check or context based interpretation systems. The most effective comparable systems approach an average of 85% accuracy in recognition of misspelled or jumbled words. The Theseus technology approaches 100%.

This new technology can be applied to any system that requires human input, such as word processing, data entry, communications, etc. The Theseus system can be used in conjunction with our Proteus technology to create conversational interfaces that far outperform previous more limited technologies.

Applications for this new software include but are not limited to: fault tolerant human input, optical text recognition systems, spell-check systems, automated translation systems, Spam filtering systems, automated data recovery, etc.

The downloadable demonstration program available from our downloads page uses a limited version of the Theseus engine. Our commercial version utilizes a multiple agent competing architecture to maximize recognition capability. The demonstration software allows only a single set of "fuzzy weights" to be utilized for analysis at a time, whereas the full version simultaneously applies multiple approaches to recognize the content. The system has multiple settings to balance between maximizing accuracy or performance.

We are currently exploring extensions of this technology in areas such as visual object recognition, object categorization/catalog systems, and fast analogical approximation.

Announcement 6/27/2005:

Multi-Systems, Inc. implements "Athena Search System" based upon Theseus Technology to provide fuzzy searching of multiple Gigabyte text database of support call histories.

Athena Search details

*Note: Please feel free to contact us to discuss similar large text indexing and search projects. In the case of the MSI project the searching index structures are updated daily, but in other large search projects could be 3 hours or less behind real-time. In addition to local text database searching this technology can be utilized with the addition of a web crawler to implement a web search engine.

Return to Research

Home