Title :
An improved neural network for segmenting objects´ boundaries in real images
Author :
Leow, Wee Kheng ; Lua, Seet Chong
Author_Institution :
Dept. of Inf. Syst. & Comput. Sci., Nat. Univ. of Singapore, Singapore
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 (1985) 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
Keywords :
image segmentation; neural nets; object recognition; boundary contour system; boundary segmentation; edge detection; object recognition; objects boundaries segmentation; silhouette images; synthetic images; Computer science; Image edge detection; Image recognition; Image segmentation; Information systems; Intelligent networks; Machine vision; Neural networks; Object recognition; Shape;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.614144
