Journal of Systems Engineering and Electronics ›› 2020, Vol. 31 ›› Issue (1): 56-63.doi: 10.21629/JSEE.2020.01.07

• Electronics Technology • Previous Articles     Next Articles

A distribution prior model for airplane segmentation without exact template

Ming DAI(), Zhiheng ZHOU*(), Yongfan GUO()   

  • Received:2019-05-13 Online:2020-02-20 Published:2020-02-25
  • Contact: Zhiheng ZHOU E-mail:dai.ming@mail.scut.edu.cn;zhouzh@scut.edu.cn;guoyonfan@163.com
  • About author:DAI Ming was born in 1991. He received his B.E. degree in mathematics and applied mathematics, South China University of Technology, Guangzhou, China in 2014. He is currently a Ph.D. student with School of Electronics and Information Engineering, South China University of Technology. His research orientations are image processing and deep learning.E-mail: dai.ming@mail.scut.edu.cn|ZHOU Zhiheng was born in 1977. He received his B.S. and M.S. degrees in Department of Applied Mathematics from South China University of Technology, Guangzhou, China, in 2000 and 2002, respectively. In 2005, he received his Ph.D. degree in School of Electronics and Information Engineering, South China University of Technology. Now he is a professor and his research interests are image processing and image and video transmission. E-mail: zhouzh@scut.edu.cn|GUO Yongfan was born in 1996. He is currently a postgraduate with School of Electronics and Information Engineering, South China University of Technology. His research orientations are image processing and deep learning. E-mail: guoyonfan@163.com
  • Supported by:
    the National Key R & D Program of China(2018YFC0309400);the National Natural Science Foundation of China(61871188);This work was supported by the National Key R & D Program of China (2018YFC0309400) and the National Natural Science Foundation of China (61871188)

Abstract:

In many practical applications of image segmentation problems, employing prior information can greatly improve segmentation results. This paper continues to study one kind of prior information, called prior distribution. Within this research, there is no exact template of the object; instead only several samples are given. The proposed method, called the parametric distribution prior model, extends our previous model by adding the training procedure to learn the prior distribution of the objects. Then this paper establishes the energy function of the active contour model (ACM) with consideration of this parametric form of prior distribution. Therefore, during the process of segmenting, the template can update itself while the contour evolves. Experiments are performed on the airplane data set. Experimental results demonstrate the potential of the proposed method that with the information of prior distribution, the segmentation effect and speed can be both improved efficaciously.

Key words: image segmentation, active contour model (ACM), prior distribution, level set method