Multiple instance subspace learning via partial random projection tree for local reflection symmetry in natural images. (April 2016)

• Record Type: Journal Article
• Authors: Shen, Wei; Bai, Xiang; Hu, Zihao; Zhang, Zhijiang
• Is Part Of: Pattern recognition. Volume 52(2016:Apr.)
• Page Start: 306
• Page End: 316
• Publication Date: 2016-04
• Subjects: Symmetry detection -- Multiple instance subspace learning -- Partial random projection tree; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2015.10.015
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Local reflection symmetry detection in nature images is a quite important but challenging task in computer vision. The main obstacle is both the scales and the orientations of symmetric structure are unknown. The multiple instance learning (MIL) framework sheds lights onto this task owing to its capability to well accommodate the unknown scales and orientations of the symmetric structures. However, to differentiate symmetry vs non-symmetry remains to face extreme confusions caused by clutters scenes and ambiguous object structures. In this paper, we propose a novel multiple instance learning framework for local reflection symmetry detection, named multiple instance subspace learning (MISL), which instead learns a group of models respectively on well partitioned subspaces. To obtain such subspaces, we propose an efficient dividing strategy under MIL setting, named partial random projection tree (PRPT), by taking advantage of the fact that each sample (bag) is represented by the proposed symmetry features computed at specific scale and orientation combinations (instances). Encouraging experimental results on two datasets demonstrate that the proposed local reflection symmetry detection method outperforms current state-of-the-arts. Abstract : Highlights: We perform clustering on samples represented by multiple instances. We learn a group of MIL classifiers on subspaces. We report state-of-the-arts results on the symmetry detection benchmark.