Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/99535
Title: Improved neural network for segmenting objects' boundaries in real images
Authors: Leow, Wee Kheng 
Lua, Seet Chong
Issue Date: 1997
Citation: Leow, Wee Kheng,Lua, Seet Chong (1997). Improved neural network for segmenting objects' boundaries in real images. IEEE International Conference on Neural Networks - Conference Proceedings 3 : 1663-1668. ScholarBank@NUS Repository.
Abstract: An important task in object recognition is to first identify the boundaries of the objects in the input image. Several neural networks have been proposed to perform edge detection and boundary segmentation. Among them, Grossberg and Mingolla's Boundary Contour System (BCS) seems promising because it is able to complete missing object boundaries. Although BCS has been shown to work well on synthetic and silhouette images, we found that it has some shortcomings when applied to real images. This paper presents an improved version of BCS for handling the shortcomings.
Source Title: IEEE International Conference on Neural Networks - Conference Proceedings
URI: http://scholarbank.nus.edu.sg/handle/10635/99535
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

20
checked on Jul 6, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.