TY - JOUR
T1 - Character recognition
T2 - Qualitative reasoning and neural networks
AU - Rodin, Ervin Y.
AU - Wu, Yuanlan
AU - Amin, S. Massoud
N1 - Funding Information:
*This research was supported by AFOSR under Grant No. 890158.
PY - 1992/2
Y1 - 1992/2
N2 - Traditional character recognition methods construct a grid and represent a character as a combination of grid dots. By using a qualitative representation method [1,2], we introduce here a new approach to representing English letters. Using properties of the qualitative representation method, we can uniquely represent each English letter regardless of the size and position of each stroke on the board. Our success of implementation by neural networks shows the feasibility of the method, and our tolerance tests show its robustness.
AB - Traditional character recognition methods construct a grid and represent a character as a combination of grid dots. By using a qualitative representation method [1,2], we introduce here a new approach to representing English letters. Using properties of the qualitative representation method, we can uniquely represent each English letter regardless of the size and position of each stroke on the board. Our success of implementation by neural networks shows the feasibility of the method, and our tolerance tests show its robustness.
UR - http://www.scopus.com/inward/record.url?scp=0142076234&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0142076234&partnerID=8YFLogxK
U2 - 10.1016/0895-7177(92)90010-I
DO - 10.1016/0895-7177(92)90010-I
M3 - Article
AN - SCOPUS:0142076234
SN - 0895-7177
VL - 16
SP - 95
EP - 104
JO - Mathematical and Computer Modelling
JF - Mathematical and Computer Modelling
IS - 2
ER -
