A novel adaptive partial differential equation model for image segmentation

Abstract

Many partial differential equation (PDE) models have been proposed for image segmentation. However, most of them cannot handle the complicated images such as inhomogeneous images. To overcome the limitation of traditional PDE-based models, a novel PDF model is proposed in this paper and then successfully applied to inhomogeneous image segmentation task. The new PDE model contains the global statistical information and local statistical information, which are balanced using an adaptive weight parameter. Some inhomogeneous images are selected for evaluations. Experimental results show that the proposed method is more effective to segment images with in-homogeneity or low contrast, without choosing the weight parameter between global and local information.

Keywords:

• image segmentation
• level set method
• PDE
• adaptive parameter
• geometric active contour model

AMS Subject Classifications:

• 42C40; 68U10

Acknowledgements

The authors also acknowledge the Key Laboratory of Medical Image Processing in Southern Medical University for providing original medical images for experiment.

Notes

1 This paper is partially supported by NSFC(61272252), Science & Technology Planning Project of Shenzhen City(JCYJ20130326111024546,JCYJ20120613102415154, ZYC201105130115A).