Yihua Lan
School of Computer and Information Technology, Nanyang Normal University, Nanyang, 473061, China
Xingang Zhang
School of Computer and Information Technology, Nanyang Normal University, Nanyang, 473061, China
Zhidu Liu
School of Computer and Information Technology, Nanyang Normal University, Nanyang, 473061, China
Li Zhao
School of Computer and Information Technology, Nanyang Normal University, Nanyang, 473061, China
Ming Li
School of Computer and Information Technology, Nanyang Normal University, Nanyang, 473061, China
ABSTRACT
With the advantages of being painless, safe and easy-to-use, wireless capsule endoscopy has become a hot research topic in clinical medicine. As tens of thousands of images are generated during an examination, it is impractical for manual image checking. Utilizing computer image processing can greatly enhance image quality, decrease diagnosis time and improve diagnosis accuracy. One of the critical requirements of the employed image processing methods is to extract the lesion areas. Although, many image segmentation methods have been proposed, accurate image segmentation is also a challenging problem which is not completely solved yet. At present, those segmentation approaches can be divided into two main categories: Region based and edge based. It is often difficult to obtain satisfactory results when using only one of these methods in the segmentation of complex pictures. Therefore, in this study, a new image segmentation method using both region and edge information is proposed to combine the two types of methods or information to achieve accurate segmentation results. Experimental results demonstrate the efficacy of the proposed method.
PDF References
How to cite this article
Yihua Lan, Xingang Zhang, Zhidu Liu, Li Zhao and Ming Li, 2013. Hybrid Segmentation Using Region Information for Wireless Capsule Endoscopy Image. Information Technology Journal, 12: 3815-3819.
DOI: 10.3923/itj.2013.3815.3819
URL: https://scialert.net/abstract/?doi=itj.2013.3815.3819
DOI: 10.3923/itj.2013.3815.3819
URL: https://scialert.net/abstract/?doi=itj.2013.3815.3819
REFERENCES
- Zhang, Z., C. Chen, J. Sun and K.L. Chan, 2003. EM Algorithms for Gaussian mixtures with split-and-merge operation. Patt. Recog., 36: 1973-1983.
CrossRef - Mendoza, C.S., B. Acha, C. Serrano and T. Gomez-Cha, 2012. Fast parameter-free region growing segmentation with application to surgical planning. Machine Vision Appli., 23: 165-177.
CrossRef - Guliato, D., R.M. Rangayyan, J.A. Zuffo and J.L. Desautels, 1998. Detection of breast tumor boundaries using iso-intensity contours and dynamic thresholding. Digital Mammography, 13: 253-260.
CrossRef - Petrick, N., H.P. Chan, B. Sahiner and M.A. Helvie, 1999. Combined adaptive enhancement and region-growing segmentation of breast masses on digitized mammograms. Med. Phys., 26: 1642-1654.
Direct Link - Timp, S. and N. Karssemeijer, 2004. A new 2D segmentation method based on dynamic programming applied to computer aided detection in mammography. Med. Phys., 31: 958-971.
PubMed - Kass, M., A. Witkin and D. Terzopoulos, 1988. Snakes: Active contour models. Int. J. Comput. Vision, 1: 321-331.
CrossRefDirect Link - Chan, T.F. and L.A. Vese, 2001. Active contours without edges. IEEE Trans. Image Process., 10: 266-277.
CrossRefDirect Link - Caselles, V., R. Kimmel and G. Sapiro, 1997. Geodesic active contours. Int. J. Comput. Vision, 22: 61-79.
CrossRefDirect Link - Bresson, X., S. Esedoglu, P. Vandergheynst, J.P. Thiran and S. Osher, 2007. Fast global minimization of the active contour/snake model. J. Math. Imaging Vision, 28: 151-167.
CrossRef - Comaniciu, D. and P. Meer, 1997. Robust analysis of feature spaces: Color image segmentation. Proceedings of the 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 17-19, 1997, San Juan, pp: 750-755.
CrossRef - Shi, J. and J. Malik, 1997. Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 22: 888-905.
Direct Link - Adams, R. and L. Bischof, 1994. Seeded region growing. IEEE Trans. Pattern Anal. Mach. Intell., 16: 641-647.
CrossRefDirect Link