A hierarchical neural network architectu
β
J. Cao; M. Ahmadi; M. Shridhar
π
Article
π
1997
π
Elsevier Science
π
English
β 532 KB
This paper presents a hierarchical neural network architecture for recognition of handwritten numeral characters. In this new architecture, two separately trained neural networks connected in series, use the pixels of the numeral image as input and yield ten outputs, the largest of which identifies