Thumbnail
Access Restriction
Open

Author Robinson, Tony
Source CiteSeerX
Content type Text
Publisher MIT Press
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Posterior Distribution ♦ Forward-backward Retraining ♦ Supervised Training Algorithm ♦ Target Output ♦ Error Rate ♦ Cheque Processing ♦ Machine Transcription ♦ Novel Method ♦ Handwritten Word ♦ Previous Publication ♦ Recurrent Neural Network ♦ Handwritten Document ♦ Historical Document Reading ♦ Personal Correspondence Reading ♦ Hidden Markov Model ♦ Forwardbackward Algorithm ♦ Off-line Handwriting Recognition ♦ Postal Sorting ♦ Letter Posterior Probability Estimator ♦ Recognition System
Description In Advances In Neural Information Processing Systems 8
This paper describes the training of a recurrent neural network as the letter posterior probability estimator for a hidden Markov model, off-line handwriting recognition system. The network estimates posterior distributions for each of a series of frames representing sections of a handwritten word. The supervised training algorithm, backpropagation through time, requires target outputs to be provided for each frame. Three methods for deriving these targets are presented. A novel method based upon the forwardbackward algorithm is found to result in the recognizer with the lowest error rate. 1 Introduction In the field of off-line handwriting recognition, the goal is to read a handwritten document and produce a machine transcription. Such a system could be used for a variety of purposes, from cheque processing and postal sorting to personal correspondence reading for the blind or historical document reading. In a previous publication (Senior 1994) we have described a system based on a ...
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 1996-01-01