Title :
Scalable parallel processing design for real time handwritten OCR
Author :
Cuhadar, A. ; Downton, A.C.
Author_Institution :
Dept. of Electron. Syst. Eng., Essex Univ., Colchester, UK
Abstract :
This paper presents a generalised technique for parallelising embedded computer vision and pattern recognition applications and shows how it has been applied to the recognition of handwritten postcodes on envelopes. The technique is based upon the utilisation of pipelines of processor farms (PPF), and is applicable to any embedded system with continuous input/output data streams. The postcode recogniser combines temporal multiplexing and data parallelism to achieve a speedup of 21.4 compared with the original sequential application, using a total of 52 transputers
Keywords :
computer vision; computer vision; pattern recognition; postcode recogniser; real time handwritten OCR; scalable parallel processing; temporal multiplexing; Computer vision; Concurrent computing; Dictionaries; Handwriting recognition; Optical character recognition software; Parallel processing; Pipelines; Process design; Systems engineering and theory; Throughput;
Conference_Titel :
Pattern Recognition, 1994. Vol. 3 - Conference C: Signal Processing, Proceedings of the 12th IAPR International Conference on
Conference_Location :
Jerusalem
Print_ISBN :
0-8186-6275-1
DOI :
10.1109/ICPR.1994.577194
