DocumentCode
2692473
Title
Applying a Hopfield-style network to degraded text recognition
Author
Jagota, Arun
fYear
1990
fDate
17-21 June 1990
Firstpage
27
Abstract
A Hopfield-style network model was developed and analyzed in detail by the author. This model has the advantage of higher storage capacity and less interference between stored memories than the classical discrete Hopfield network. The model is applied to machine printed word recognition. Words to be recognized are stored as content-addressable memories. Word images are first processed by an OCR. The network is then used to postprocess the OCR decisions
Keywords
character recognition; content-addressable storage; neural nets; Hopfield-style network; OCR; content-addressable memories; degraded text recognition; higher storage capacity; machine printed word recognition; stored memories; word images;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1990., 1990 IJCNN International Joint Conference on
Conference_Location
San Diego, CA, USA
Type
conf
DOI
10.1109/IJCNN.1990.137539
Filename
5726502
Link To Document