Adaptive appearance separation for interactive image segmentation based on Dense CRF. Issue 1 (1st January 2019)

• Record Type: Journal Article
• Authors: Peng, Zili; Li, Qiaoliang
• Is Part Of: IET image processing. Volume 13:Issue 1(2019)
• Page Start: 142
• Page End: 151
• Publication Date: 2019-01-01
• Subjects: image colour analysis -- learning (artificial intelligence) -- image segmentation; adaptive appearance separation -- interactive image segmentation -- Dense CRF -- interactive segmentation -- hot topic -- wide application -- efficacious appearance separation model -- interactive binary segmentation -- foreground -- background colour models -- corresponding geodesic models -- popular densely connected conditional random field framework -- relevant parameter values -- target images -- per‐image manner -- mean‐field inference -- time‐consuming parameter -- segmentation efficiency -- scribble‐style interaction; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.5073
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Interactive segmentation has recently become a hot topic for its wide application. The authors propose an efficacious appearance separation model for interactive binary segmentation, which incorporates the difference of foreground and background colour models and the difference of corresponding geodesic models into the popular densely connected conditional random field (Dense CRF) framework. The proposed method can adaptively set relevant parameter values in this framework according to the characteristics of target images in a per‐image manner, therefore, it gets rid of the dependence on specific datasets. After accomplishing a mean‐field inference, the authors are able to get satisfactory results without the time‐consuming parameter learning process and multiple iterative optimisations. Overall, the proposed approach is highly efficient and mitigates the contradiction between accuracy and segmentation efficiency. In addition, the proposed approach reduces the efforts of scribble‐style interaction from users. The experimental results on three famous datasets show that the proposed method is superior to the other five new algorithms released in recent years regarding accuracy, and is faster than or close to them in runtime.