|
KMID : 1146720170040010021
|
|
국제컴퓨터가상수술학회 학술지
2017 Volume.4 No. 1 p.21 ~ p.23
|
|
|
Inversion of Spread-Direction and Alternate Neighborhood System for Cellular Automata-Based Image Segmentation Framework
|
|
Lee Kyung-Jae
Lee Jun-Hyeop
Hwang Sang-Won
Lee Sang-Youn
|
|
|
Abstract
|
|
|
Purpose: In this paper, we proposed alternate neighborhood system and reverse spread-direction approach for accurate and fast cellular automata-based image segmentation method.
Materials and Methods: On the basis of a simple but effective interactive image segmentation technique based on a cellular automaton, we propose an efficient algorithm by using Moore and designed neighborhood system alternately and reversing the direction of the reference pixels for spreading out to the surrounding pixels.
Results: In our experiments, the GrabCut database were used for evaluation. According to our experimental results, the proposed method allows cellular automata-based image segmentation method to faster while maintaining the segmentation quality.
Conclusion: Our results proved that proposed method improved accuracy and reduced computation time, and also could be applied to a large range of applications.
|
|
|
KEYWORD
|
|
|
Image segmentation, Cellular Automata, Medical Image
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|
|