Revisiting graph construction for fast image segmentation. (June 2018)

• Record Type: Journal Article
• Authors: Zhang, Zizhao; Xing, Fuyong; Wang, Hanzi; Yan, Yan; Huang, Ying; Shi, Xiaoshuang; Yang, Lin
• Is Part Of: Pattern recognition. Volume 78(2018:Jun.)
• Page Start: 344
• Page End: 357
• Publication Date: 2018-06
• Subjects: Image segmentation -- Graph partition -- Manifold; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2018.01.037
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A novel way to construct graph for very fast image segmentation with global and local energy functions is proposed. Various high-level cues (co-occurrence and saliency) to help build the graphs are developed. A fast graph partition optimization objective is proposed. A multi-class segmentation method using simple EigenHistograms is pro- posed. Extensive experiments on BSDS500, PASCAL VOC, and COCO datasets are conducted to demonstrate the effectiveness of the proposed method. Abstract: In this paper, we propose a simple but effective method for fast image segmentation. We re-examine the locality-preserving character of spectral clustering by constructing a graph over image regions with both global and local connections. Our novel approach to build graph connections relies on two key observations: 1) local region pairs that co-occur frequently will have a high probability to reside on a common object; 2) spatially distant regions in a common object often exhibit similar visual saliency, which implies their neighborship in a manifold. We present a novel energy function to efficiently conduct graph partitioning. Based on multiple high quality partitions, we show that the generated eigenvector histogram based representation can automatically drive effective unary potentials for a hierarchical random field model to produce multi-class segmentation. Sufficient experiments, on the BSDS500 benchmark, large-scale PASCAL VOC and COCO datasets, demonstrate the competitive segmentation accuracy and significantly improved efficiency of our proposed method compared with other state of the arts.