Low-complexity arrays of contour signatures for exact shape retrieval
作者：
Highlights：
• A complete framework for exact shape retrieval with near-constant complexity.
• Signatures are a compact way to gather relevant information about a contour.
• Feature pairs of signature extrema add structural information.
• Pair descriptors are stored into a system of associative arrays.
• The technique is very fast and robust to rigid transformations and noise.
摘要
•A complete framework for exact shape retrieval with near-constant complexity.•Signatures are a compact way to gather relevant information about a contour.•Feature pairs of signature extrema add structural information.•Pair descriptors are stored into a system of associative arrays.•The technique is very fast and robust to rigid transformations and noise.
论文关键词：Shape recognition,Contour signature,Fast retrieval,Associative arrays
论文评审过程：Received 23 May 2020, Revised 24 March 2021, Accepted 18 April 2021, Available online 1 May 2021, Version of Record 1 June 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108000
