Robust detectors of rotationally symmetric shapes based on novel semi-shape signatures. (June 2023)

• Record Type: Journal Article
• Authors: Nguyen, Thanh Phuong; Nguyen, Thanh Tuan
• Is Part Of: Pattern recognition. Volume 138(2023)
• Publication Date: 2023-06
• Subjects: Rotational symmetry detection -- LIP/R-signature -- Radon; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2023.109336
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Solid theoretical foundation of a novel semi-shape concept for analyzing the rotationally symmetric attributes of a shape. Two new projection-based signatures of a shape based on the correlation between its semi-shapes. A meaningful measure for semi-shape profiles to determine a perfect level of rotational symmetry. Robust detectors for rotationally symmetric shapes based on LIP s / R s -signature correspondingly. A novel dataset, named HCMUTE-RotaShape, including single/compound shapes with challenging rotation properties. Comprehensive evaluations have verified that the proposed detectors executed well in comparison with state of the art. Abstract: Efficient detectors of rotationally symmetric shapes are proposed by introducing a novel concept of semi-shape signatures to overcome the main problem of projection-based approaches for studying the rotationally symmetric properties of an arbitrary binary shape. Indeed, the fact that the projection cues in these conventional approaches are periodical with a period of π has restricted an applicable exploitation of rotational symmetry detection. To this end, we propose a new concept of the profile of semi-shapes as a shape signature together with a simple yet efficient technique so that the rotational symmetry of the binary shape can be determined by considering the correlation between this signature and its circular shift. Moreover, a new meaningful measure, ranging from 0 to 1, is also introduced to indicate how perfect the rotational symmetry would be. Experimental results of detecting on single/compound shapes have clearly corroborated the competence of our proposal.