Title :
Methods for enhancing neural network handwritten character recognition
Author :
Garris, M.D. ; Wilkinson, R.A. ; Wilson, C.L.
Author_Institution :
Nat. Inst. of Stand. & Technol., Gaithersburg, MD, USA
Abstract :
An efficient method for increasing the generalization capacity of neural character recognition is presented. The network uses a biologically inspired architecture for feature extraction and character classification. The numerical methods used are optimized for use on massively parallel array processors. The method for training set construction, when applied to handwritten digit recognition, yielded a writer-independent recognition rate of 92%. The activation strength produced by network recognition is an effective statistical confidence measure of the accuracy of recognition. A method of using the activation strength for reclassification is described which, when applied to handwritten digit recognition, reduced substitutional errors to 2.2%
Keywords :
character recognition; computerised pattern recognition; neural nets; parallel algorithms; accuracy; activation strength; biologically inspired architecture; character classification; digit recognition; feature extraction; generalization capacity; handwritten character recognition; massively parallel array processors; neural network; numerical methods; reclassification; statistical confidence measure; substitutional errors; training set construction; writer-independent recognition rate; Bayesian methods; Character recognition; Error analysis; Feature extraction; Handwriting recognition; Image reconstruction; Least squares methods; NIST; Neural networks; Optimization methods;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155265
