Supervised image segmentation based on superpixel and improved normalised cuts. Issue 12 (2nd September 2019)

• Record Type: Journal Article
• Authors: Qu, Shaojun; Li, Qiaoliang; Chen, Ming
• Is Part Of: IET image processing. Volume 13:Issue 12(2019)
• Page Start: 2204
• Page End: 2212
• Publication Date: 2019-09-02
• Subjects: image segmentation -- computer vision -- graph theory -- interactive systems; supervised image segmentation -- effective image segmentation -- efficient image segmentation -- computer vision -- full‐automatic image segmentation -- interactive image segmentation method -- cannot‐link constraints -- superpixel regions -- natural image segmentation -- improved normalised cuts -- must‐link constraints -- Bhattacharyya distance; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.6241
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Effective and efficient image segmentation is an important task in computer vision. As the full‐automatic image segmentation is usually difficult to segment the natural image, it is an excellent solution to use interactive schemes. Here, to overcome the defects of SSNCut in its low quality and speed, the authors proposed a new interactive image segmentation method based on superpixels, must‐link, cannot‐link constraints and improved normalised cuts. The main contribution of their work is as follows: first, the similarity between two superpixel regions is calculated using Bhattacharyya distance. Second, they adaptively modify the weights of must‐link and cannot‐link constraints. Compared to SSNCut, their method greatly improves the accuracy of segmentation. Comparative experiments on open datasets show that the proposed method can get better results compared with SSNCut, GrabCut in one cut, interactive segmentation using binary partition tree, interactive graph cut, seed region growing, and simple interactive object extraction.