Applying a Hopfield-style network to degraded text recognition
Arun Jagota · 1990
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