A unified object-oriented toolkit for discrete contextual computer vision
A unified object-oriented toolkit for discrete contextual computer vision
- Author(s): L. Du ; A.C. Downton ; S.M. Lucas
- DOI: 10.1049/ic:19970126
For access to this article, please select a purchase option:
Buy conference paper PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
IEE Colloquium on Pattern Recognition — Recommend this title to your library
Thank you
Your recommendation has been sent to your librarian.
- Author(s): L. Du ; A.C. Downton ; S.M. Lucas Source: IEE Colloquium on Pattern Recognition, 1997 page ()
- Conference: IEE Colloquium on Pattern Recognition
This paper describes a new general-purpose contextual architecture which provides a unified framework for efficiently combining all types and levels of context in discrete computer vision applications, by organising the multidimensional search space in best-first order along each dimension. It then implements an efficient `lazy evaluation' algorithm, which searches from the most probable vertex outwards, and guarantees to find solutions in absolute best-first order. The architecture has been designed and built as a C++ class library, and utilised within a demonstrator which implements full contextual constraints for optical character recognition of hand-printed postal addresses. Preliminary evaluation of the demonstrator suggests the system has the potential to achieve genuinely remarkable performance compared with previous context systems: its memory requirements are an order of magnitude less than an equivalent trie-based dictionary; its search speed is at least an order of magnitude faster than the trie, and actually get faster as the dictionary size increases; and its error rate is virtually zero, even when an OCR system with appalling performance is simulated. Using this architecture it appears to be possible to build real-time solutions to large-scale contextual vision problems which have previously been beyond the bounds of computational feasibility. (5 pages)
Inspec keywords: image recognition; search problems; object-oriented methods; optical character recognition; computer vision; neural nets
Subjects: Computer vision and image processing techniques; Formal methods; Neural nets (theory); Neural computing techniques; Optical information, image and video signal processing; Pattern recognition
Related content
content/conferences/10.1049/ic_19970126
pub_keyword,iet_inspecKeyword,pub_concept
6
6