Using a Viewing Window and the HAVNET Neural Network for the Recognition of Words within a Document


A substantial portion of research and applications for visual image recognition has been limited to the recognition of large, isolated, non-variant images. Performing a visual search for focusing on, locating, and recognizing smaller details within the context of a larger image has proven more difficult. This paper presents a system that is capable of learning words of various lengths, and then locating and recognizing a previously trained word within a noisy document. This system utilizes a fitness function, search routine and viewing window to identify possible word candidates, and then employs the HAusdorff-Voronoi NET work (HAVNET) for word recognition. After 330 searches of 30 different words, with document noise ranging from 0-20%, the system recognition and location accuracy was 97.3%.


Electrical and Computer Engineering

Second Department

Engineering Management and Systems Engineering

Keywords and Phrases

Fovea; HAVNET; Neural networks; Pattern recognition; Viewing window; Word

International Standard Serial Number (ISSN)

1996-756X; 0277-786X

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type





© 2024 Society of Photo-optical Instrumentation Engineers, All rights reserved.

Publication Date

06 Apr 1995