Genetic programming-based learning of texture classification descriptors from Local Edge Signature
作者：
Highlights：
• Local Edge Signature is a geometric-insensitive operator that represents texture.
• Local Edge Signature is based on edge pixels’ arrangements and orientations.
• A genetic programming technique learns automatically a global texture descriptor.
• A tree representation of individuals generates global texture features.
• Generated descriptor needs few training images to extract discriminative features.
摘要
•Local Edge Signature is a geometric-insensitive operator that represents texture.•Local Edge Signature is based on edge pixels’ arrangements and orientations.•A genetic programming technique learns automatically a global texture descriptor.•A tree representation of individuals generates global texture features.•Generated descriptor needs few training images to extract discriminative features.
论文关键词：Texture classification,Genetic programming,Texture descriptor,Feature extraction,Local Edge Signature
论文评审过程：Received 21 June 2019, Revised 30 May 2020, Accepted 13 June 2020, Available online 29 June 2020, Version of Record 10 July 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113667
