DocumentCode
1642331
Title
Neural network recognition of magnetic ink code line using magnetically sensed time variant signal
Author
Mostert, S. ; Van Rensburg, JJ ; Goosen, N.
Author_Institution
Stellenbosch Univ., South Africa
fYear
1992
fDate
9/11/1992 12:00:00 AM
Firstpage
259
Lastpage
264
Abstract
This paper provides a solution unique in that the speed varies with the person swiping the check past the head, and the recognition is made without any additional timing information. Techniques applied and researched vary from neural networks to various heuristics based on the properties of the signal derived from the magnetic sense head. The neural network recognition is explored in more detail to find the most optimal solution
Keywords
cheque processing; heuristic programming; magnetic fluids; magnetic heads; mark scanning equipment; neural nets; cheque processing; heuristics; magnetic sense head; magnetically sensed time variant signal; neural network; recognition of magnetic ink code line; Character recognition; Cost function; Feeds; Ink; Magnetic flux; Magnetic heads; Magnetic properties; Magnetic separation; Neural networks; Timing;
fLanguage
English
Publisher
ieee
Conference_Titel
Communications and Signal Processing, 1992. COMSIG '92., Proceedings of the 1992 South African Symposium on
Conference_Location
Cape Town
Print_ISBN
0-7803-0807-7
Type
conf
DOI
10.1109/COMSIG.1992.274274
Filename
274274
Link To Document