Massively parallel implementation of character recognition systems
Michael D. Garris, C L Wilson, James L. Blue, Gerald T. Candela, P Grother, Stanley A. Janet, R. Allen Wilkinson · 1992
A massively parallel character recogniuon system has been implemented.The system is designed to study the feasibility of the recogniuon of handprinted text in a loosely constrained environment The NIST handprint database,NIST Special Database 1, is used to provide test data for the recogniuon system.The system consists of eight funcdonal components.The loading of the image into the system and storing the recogniuon results from the system are I/O components.In between are components responsible for image processing and recognition.The first image processing component is responsible for image correcuon for scale and rotauon, data field isolation, and character data locadon within each field; the second performs character segmentauon; and the third does character normalizadon.Three recog- niuon components are responsible for feature extracuon and character reconstrucuon, neural network-based character recogniuon, and low-confidence classification rejection.The image processing to load and isolate 34 fields on a scientific workstation takes 900 seconds.The same processing takes only 11 seconds using a massively parallel array processor.The image processing components, including the time to load the image data, use 94% of the system time.The segmentation time is 15 ms/character and segmentation accuracy is 89% for hand- printed digits and alphas.Character recognition accuracy for medium quality machine print is 99.8%.On handprinted digits, the recognition accuracy is 96% and recognition speeds of 10,100 characters/second can be realized.The limiting factor in the recog- nition portion of the system is feature extraction, which occurs at 806 characters/second.Through the use of a massively parallel machine and neural recognition algorithms, significant improvements in both accuracy and speed have been achieved, making this technology effective as a replacement for key data entry in existing data capture systems.