A Novel Approach to Simultaneous Image Segmentation and Bias Correction

This paper presents a variational level set approach to joint segmentation and bias correction of images with intensity in homogeneity. Our method is based on an observation that intensities in a relatively small local region are separable, despite of the inseparability of the intensities in the whole image caused by the intensity in homogeneity. We first define a weighted K-means clustering objective function for image intensities in a neighbourhood around each point, with the cluster centres having a multiplicative factor that estimates the bias within the neighbourhood. The objective function is then integrated over the entire domain and incorporated into a variational level set formulation. The energy minimization is performed via a level set evolution process. Our method is able to estimate bias of quite general profiles. Moreover, it is robust to initialization, and therefore allows automatic applications. The proposed method has been used for images of various modalities with promising results.