CHARACTER-RECOGNITION USING A FAST NEURAL-NET CLASSIFIER

被引:4
|
作者
LI, RY
XU, M
机构
[1] Department of Electrical Engineering, University of Nebraska, Lincoln
关键词
CHARACTER RECOGNITION; MOMENT INVARIANTS; NEURAL-NET CLASSIFIER; CORRELATION-BASED LEARNING VECTOR ANALYSIS;
D O I
10.1016/0167-8655(92)90034-W
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A correlation-based neural-net classifier is used to classify printed characters using moment invariants as the feature inputs. This classifier drastically reduces the training time by setting up initial weights and a hidden layer structure more suitable for fast convergence.
引用
收藏
页码:369 / 374
页数:6
相关论文
共 50 条