A bias correction variational level set image segmentation model combining structure extraction
Xili Wang, Li Hu, Xiyuan Wang · 2017
The authors propose a variational level set image segmentation method for intensity inhomogeneous texture image. The method first extracts the main image structure by a relative total variation image decomposition method, which can better decompose the image into structural and textural parts. Then only uses the structural part as the input image for the variational level set segmentation. The intensity bias are estimated simultaneously in the level set curve evolution procedure. And the intensity inhomogeneity is solved by bias correction. The experiments indicate that the proposed method can remove texture, retain and smooth the structure information, estimate and correct intensity bias effectively. Thus, it improves the segmentation results compared with the level set image segmentation methods that take no account of intensity inhomogeneity and texture in images.