A cellular automata approach to local patterns for texture recognition

作者：

Highlights：

• We propose a cellular automata approach to texture recognition.

• Transition function based on local binary features.

• Chaotic evolution controlled by a weighting parameter.

• The method is evaluated on the classification of benchmark textures.

• State-of-the-art methods are outperformed in terms of classification accuracy.

摘要

•We propose a cellular automata approach to texture recognition.•Transition function based on local binary features.•Chaotic evolution controlled by a weighting parameter.•The method is evaluated on the classification of benchmark textures.•State-of-the-art methods are outperformed in terms of classification accuracy.

论文关键词：Cellular automata,Texture recognition,Local binary patterns,Discrete dynamical system

论文评审过程：Received 5 March 2020, Revised 16 February 2021, Accepted 6 April 2021, Available online 16 April 2021, Version of Record 2 May 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115027