Journal of Systems Engineering and Electronics ›› 2018, Vol. 29 ›› Issue (1): 187-195.doi: 10.21629/JSEE.2018.01.19

• Software Algorithm and Simulation • Previous Articles     Next Articles

Improved evidential fuzzy c-means method

Wen JIANG*(), Tian YANG(), Yehang SHOU(), Yongchuan TANG(), Weiwei HU()   

  • Received:2017-01-11 Online:2018-02-26 Published:2018-02-23
  • Contact: Wen JIANG E-mail:jiangwen@nwpu.edu.cn;yangtian@mail.nwpu.edu.cn;shouyehang@mail.nwpu.edu.cn;tangyongchuan@mail.nwpu.edu.cn;huweiweinwpu@mail.nwpu.edu.cn
  • About author:JIANG Wen was born in 1974. She received her B.S. degree in signal and system from Information Engineering University in 1994, her M.S. degree in image processing from Information Engineering University in 1997, and her Ph.D. degree in systems engineering from Northwestern Polytechnical University in 2009. She is currently a professor in School of Electronics & Information, Northwestern Polytechnical University. Her research interests are information fusion and intelligent information processing. E-mail: jiangwen@nwpu.edu.cn|YANG Tian was born in 1990. She is currently a master student in School of Electronics & Information, Northwestern Polytechnical University. She received her B.S. degree in communication engineering from Shangqiu Normal University in 2014. Now, her research interests are information fusion and intelligent information processing. She is especially interested in medical image processing, conflict information processing, image segmentation and image fusion. E-mail: yangtian@mail.nwpu.edu.cn|SHOU Yehang was born in 1992. He received his B.S. degree from Yan'an University in 2015. He is currently a master student in School of Electronics & Information, Northwestern Polytechnical University. His research interest is information fusion. Specifically, it includes D-S evidence theory approximation algorithm, fast hardware implementation of D-S evidence theory. E-mail: shouyehang@mail.nwpu.edu.cn|TANG Yongchuan was born in 1988. He received his B.S. degree in automation and his M.S. degree in computer application technology from Southwest University in 2011 and 2014, respectively. His research work in Southwest University mainly focuses on intelligent control theory especially for fuzzy control theory and its application in the linear inverted pendulum system and the planar inverted pendulum system. From 2014 to 2015, he worked as an R & D engineer in the Automotive Engineering Institute of Guangzhou Automobile Group Co, Ltd. Currently, he is a Ph.D. candidate in Northwestern Polytechnical University. His recent research interests are intelligent information processing and information fusion. E-mail: tangyongchuan@mail.nwpu.edu.cn|HU Weiwei was born in 1993. He received his B.S. degree in electronic information science and technology from Henan University of Science and Technology in 2016. Currently, he is working towards his M.S. degree in Northwestern Polytechnical University. His recent research interests are intelligent information processing and information fusion. E-mail: huweiweinwpu@mail.nwpu.edu.cn
  • Supported by:
    the National Natural Science Foundation of China(61671384);the National Natural Science Foundation of China(61703338);the Natural Science Basic Research Plan in Shaanxi Province of China(2016JM6018);the Project of Science and Technology Foundation;the Fundamental Research Funds for the Central Universities(3102017OQD020);This work was supported by the National Natural Science Foundation of China (61671384; 61703338), the Natural Science Basic Research Plan in Shaanxi Province of China (2016JM6018), the Project of Science and Technology Foundation, and the Fundamental Research Funds for the Central Universities (3102017OQD020)

Abstract:

Dempster-Shafer evidence theory (DS theory) is widely used in brain magnetic resonance imaging (MRI) segmentation, due to its efficient combination of the evidence from different sources. In this paper, an improved MRI segmentation method, which is based on fuzzy c-means (FCM) and DS theory, is proposed. Firstly, the average fusion method is used to reduce the uncertainty and the conflict information in the pictures. Then, the neighborhood information and the different influences of spatial location of neighborhood pixels are taken into consideration to handle the spatial information. Finally, the segmentation and the sensor data fusion are achieved by using the DS theory. The simulated images and the MRI images illustrate that our proposed method is more effective in image segmentation.

Key words: average fusion, spatial information, Dempster-Shafer evidence theory (DS theory), fuzzy c-means (FCM), magnetic resonance imaging (MRI), image segmentation