DocumentCode
2389927
Title
Boundary detection based on neural networks model
Author
Hung, D. C Douglas ; Chen, K.T.
Author_Institution
Dept. of Comput. & Inf. Sci., New Jersey Inst. of Technol., Newark, NJ, USA
fYear
1991
fDate
10-13 Nov 1991
Firstpage
254
Lastpage
257
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
Keywords
learning systems; neural nets; pattern recognition; boundary detection; circular mask; feedforward; neural networks model; piecewise linearized edge; symmetrical neural network; weighted intermediate pattern; Humans; Image edge detection; Image segmentation; Information science; Neural networks; Pattern analysis; Robustness; Shape; Size measurement; Visual system;
fLanguage
English
Publisher
ieee
Conference_Titel
Tools for Artificial Intelligence, 1991. TAI '91., Third International Conference on
Conference_Location
San Jose, CA
Print_ISBN
0-8186-2300-4
Type
conf
DOI
10.1109/TAI.1991.167102
Filename
167102
Link To Document