Unified detection of skewed rotation, reflection and translation symmetries from affine invariant contour features
作者：
Highlights：
• A unified framework is proposed for detecting different symmetries on real-world images.
• Affine invariant contour matching is used to find correspondence under skewed imaging.
• A sign change criterion is proposed to classify matching pairs for different symmetries.
• Novel schemes such as that based on short line segments are proposed for symmetry voting.
• Different symmetries are detected simultaneously or separately with desired performance.
摘要
Highlights•A unified framework is proposed for detecting different symmetries on real-world images.•Affine invariant contour matching is used to find correspondence under skewed imaging.•A sign change criterion is proposed to classify matching pairs for different symmetries.•Novel schemes such as that based on short line segments are proposed for symmetry voting.•Different symmetries are detected simultaneously or separately with desired performance.
论文关键词：Symmetry detection,Contour matching,Affine invariance,Voting,Rotation symmetry,Reflection symmetry,Translation symmetry
论文评审过程：Received 1 July 2012, Revised 18 October 2013, Accepted 14 November 2013, Available online 25 November 2013.
论文官网地址：https://doi.org/10.1016/j.patcog.2013.11.016
