Abstract
A new model of feedforward neural networks is proposed for solving the problem of robust boundary detection. Structurally, it is based on a circular mask which is characterized as a symmetrical neural network. By analyzing the weighted intermediate pattern, a dominant pattern is found to appear repeatedly for similar boundary orientation. Hence, a piecewise linearized edge could be detected by this approximation. Experimental results show that this new architecture can be applied to experience scaling effect by changing the mask size.
Original language | English (US) |
---|---|
Title of host publication | Third Int Conf Tools Artif Intell |
Publisher | Publ by IEEE |
Pages | 254-257 |
Number of pages | 4 |
ISBN (Print) | 0818623004 |
State | Published - Jan 1 1992 |
Event | Third International Conference on Tools for Artificial Intelligence - San Jose, CA, USA Duration: Nov 5 1991 → Nov 8 1991 |
Other
Other | Third International Conference on Tools for Artificial Intelligence |
---|---|
City | San Jose, CA, USA |
Period | 11/5/91 → 11/8/91 |
All Science Journal Classification (ASJC) codes
- Engineering(all)