Cartoon-texture evolution for two-region image segmentation
This addresses a specific limitation in image segmentation for applications dealing with noisy or textured images, but it is incremental as it builds on prior work.
The paper tackled the problem of two-region image segmentation in images with noise or texture, where existing models fail, by proposing a new model based on cartoon-texture decomposition, which achieved accurate segmentation as demonstrated in experiments.
Two-region image segmentation is the process of dividing an image into two regions of interest, i.e., the foreground and the background. To this aim, Chan et al. [Chan, Esedoglu, Nikolova, SIAM Journal on Applied Mathematics 66(5), 1632-1648, 2006] designed a model well suited for smooth images. One drawback of this model is that it may produce a bad segmentation when the image contains oscillatory components. Based on a cartoon-texture decomposition of the image to be segmented, we propose a new model that is able to produce an accurate segmentation of images also containing noise or oscillatory information like texture. The novel model leads to a non-smooth constrained optimization problem which we solve by means of the ADMM method. The convergence of the numerical scheme is also proved. Several experiments on smooth, noisy, and textural images show the effectiveness of the proposed model.