DocumentCode :
2287814
Title :
Unstructured to structured error correction using neural nets
Author :
Al-Mashouq, K.A. ; Jabri, A. Kh Al
Author_Institution :
Dept. of Electr. Eng., King Saud Univ., Riyadh, Saudi Arabia
fYear :
1994
fDate :
13-16 Apr 1994
Firstpage :
457
Abstract :
Most transmitted or stored information are subjected to occasional errors. In most situations, the source of this information has inherent unstructured redundancy that can be exploited to correct these errors. In addition to the storage requirements, getting the source statistics required to perform the error correction may not be easy. In this paper, we propose and evaluate trained neural nets to transform the unstructured redundancy into a structured one. The new approach, eliminates the need for source statistics storage and also simplifies the decoding process. This idea is applied to correct some of the errors caused by passing a printed Arabic text through an optical character recognition (OCR) device. Simulation results demonstrate the effectiveness of this technique
Keywords :
backpropagation; decoding; error correction codes; neural nets; optical character recognition; decoding; error correction codes; neural nets; optical character recognition device; printed Arabic text; simulation results; source statistics; storage requirements; stored information; structured error correction; trained neural nets; transmitted information; unstructured error correction; unstructured redundancy; Decoding; Error correction; Error correction codes; Image coding; Neural networks; Optical character recognition software; Optical receivers; Redundancy; Speech processing; Statistics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on
Print_ISBN :
0-7803-1865-X
Type :
conf
DOI :
10.1109/SIPNN.1994.344872
Filename :
344872
Link To Document :
بازگشت