|
|
|
| A new kind of shadow detector based on cnn-ubn |
| Wang Haiming①; Guo Shide②; Yu Daoheng① |
| ①Dept. of Electron., The Nat. Lab of Machine Perception, Peking Univ.,Beijing 100871, China;②The Institute of Remote Sensing and GIS, Peking University, China |
|
|
|
|
Abstract In this paper, a new kind of two-dimensional Cellular Automata (CA) is studied. Several algorithmic rules are discovered that can be used to design new Cellular Neural Networks (CNN) which can implement shadow detector and overstriking for character recognition. Their Boolean expressions and learning algorithms are introduced detailedly. The results of computer simulation confirm that this new approach is simpler and more effective than that given in the literature. Furthermore, these results also confirm that new CNN can be designed with CA rules and find a novel method to design CNN.
|
|
Received: 24 June 2002
|
|
|
|
|
|
|
|
|
2003, Vol. 25 
