Adaptive appearance separation for interactive image segmentation based on Dense CRF

• Published in: IET image processing Vol. 13; no. 1; pp. 142 - 151
• Main Authors: Peng, Zili, Li, Qiaoliang
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.01.2019
• Subjects: adaptive appearance separation; background colour models; corresponding geodesic models; Dense CRF; efficacious appearance separation model; foreground; hot topic; image colour analysis; image segmentation; interactive binary segmentation; interactive image segmentation; interactive segmentation; learning (artificial intelligence); mean‐field inference; per‐image manner; popular densely connected conditional random field framework; relevant parameter values; Research Article; scribble‐style interaction; segmentation efficiency; target images; time‐consuming parameter; wide application; per-image manner; background colour models; hot topic; efficacious appearance separation model; time-consuming parameter; segmentation efficiency; foreground; popular densely connected conditional random field framework; scribble-style interaction; interactive image segmentation; interactive binary segmentation; image segmentation; adaptive appearance separation; relevant parameter values; mean-field inference; wide application; image colour analysis; Dense CRF; interactive segmentation; target images; learning (artificial intelligence); corresponding geodesic models
• ISSN: 1751-9659; 1751-9667; 1751-9667
• DOI: 10.1049/iet-ipr.2018.5073

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.