A new level set segmentation based on fuzzy theory with application on mri and infrared images

作者：Liu Jin; Zhao Hang; Ji Hongbing

来源：8th International Conference on Internet Multimedia Computing and Service, ICIMCS 2016, 2016-08-19 To 2016-08-21.

DOI：10.1145/3007669.3007735

• Bias field
• Intensity inhomogeneity
• Level Set
• Level set segmentation
• Magnetic resonance images (MRI)
• MRI Image
• Regularization terms
• Segmentation results

Image segmentation is a huge task and challenge in the magnetic resonance images (MRI) and infrared images because of the intensity inhomogeneity, noisy and other problems. It is of importance to distinguish each region accurately to obtain a perfect segmentation result. Methods based on bias field theory can effectively overcome the intensity inhomogeneity. However, the edges can not be segmented well, especially for complicated shape target. Therefore, a new regularization term based on gradient is proposed to further improve the accuracy of segmentation edges in the paper. Compared with some improvement methods which based on the standard FCM and level set algorithm, the results show that the proposed method is more accurate in image segmentation for MRI and infrared images.

• 出版日期2016
• 单位西安电子科技大学