Reflection symmetry detection of shapes based on shape signatures
作者：
Highlights：
• A solid theoretical foundation of R-signature and LIP-signature about symmetric properties of a given shape is represented.
• A verification process is theoretically justified to remove the false candidates based on an efficient symmetry measure.
• Two novel datasets (UTLN-SRA & UTLN-MRA) with single & multiple reflections are designed for evaluating symmetry detectors.
• A new evaluation protocol based on a lost measure is presented to evaluate reflectional symmetry detectors.
• Comprehensive evaluations have verified that our proposed detectors perform well on binary images compared to state of the art.
摘要
•A solid theoretical foundation of R-signature and LIP-signature about symmetric properties of a given shape is represented.•A verification process is theoretically justified to remove the false candidates based on an efficient symmetry measure.•Two novel datasets (UTLN-SRA & UTLN-MRA) with single & multiple reflections are designed for evaluating symmetry detectors.•A new evaluation protocol based on a lost measure is presented to evaluate reflectional symmetry detectors.•Comprehensive evaluations have verified that our proposed detectors perform well on binary images compared to state of the art.
论文关键词：Symmetry detection,Reflection symmetry,LIP-signature,R-signature,Radon
论文评审过程：Received 27 July 2021, Revised 1 February 2022, Accepted 22 March 2022, Available online 24 March 2022, Version of Record 5 April 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.108667
