An improved GrabCut on multiscale features. (July 2020)

• Record Type: Journal Article
• Authors: He, Kun; Wang, Dan; Tong, Miao; Zhu, Zhijuan
• Is Part Of: Pattern recognition. Volume 103(2020:Jul.)
• Publication Date: 2020-07
• Subjects: Image segmentation -- GrabCut -- Multiscale feature -- Total variation regularization -- Inhomogeneity; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2020.107292
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: GrabCut model combining optimized segmentation and feature selection is proposed. Feature extraction based on multiscale decomposition was also implemented. Significant improvement was observed in case of real images. Improvement was achieved without increasing user interaction. Abstract: the GrabCut can effectively extract the foreground according to features in a cartoon image; however, the performance is not so effective for a real image, because the feature extraction is independent of segmentation. To improve segmentation performance, this paper proposes an improved GrabCut which combines the segmentation and multiscale feature extraction into a unified model. In this model, the segmentation relies on multiscale features, and the multiscale features depend on multiscale decomposition. A novel total variation regularization is proposed in multiscale decomposition to preserve edges and remove the region inhomogeneity, by which the generalization of features for segmentation is improved. The features obtained by the multiscale decomposition are integrated into the segmentation process, and the foreground can be easily extracted from a proper scale. Experimental results indicate that, compared to the existing GrabCut and improved techniques, this method provides competitive performance in terms of the segmentation accuracy, while being insensitive to inhomogeneity.