Iterated random walks with shape prior

作者：

Highlights：

• New framework using random walks combining a distance-based prior with a region term

• Prior weighted by a confidence map to reduce influence of the prior in certain areas

• A refinement might be applied using a narrow band.

• Our approach was tested with natural and medical images giving satisfactory results.

摘要

•New framework using random walks combining a distance-based prior with a region term•Prior weighted by a confidence map to reduce influence of the prior in certain areas•A refinement might be applied using a narrow band.•Our approach was tested with natural and medical images giving satisfactory results.

论文关键词：Random walks,Segmentation,Shape prior,Iterative segmentation,Distance map prior

论文评审过程：Received 16 June 2015, Revised 8 March 2016, Accepted 15 July 2016, Available online 25 July 2016, Version of Record 4 August 2016.

论文官网地址：https://doi.org/10.1016/j.imavis.2016.07.005