Rotation invariant angle-density based features for an ice image classification system

作者：

Highlights：

• We present a new expert system for ice and non-ice image classification.

• It explores wavelet decomposition to extract robust features.

• It studies the presence of ice in images systematically.

• Experiments are conducted on a new created database to show the effectiveness.

摘要

•We present a new expert system for ice and non-ice image classification.•It explores wavelet decomposition to extract robust features.•It studies the presence of ice in images systematically.•Experiments are conducted on a new created database to show the effectiveness.

论文关键词：Wavelet decomposition,Canny edge components,Major axis,Angle,Density and Multi-layer perceptron neural network

论文评审过程：Received 8 April 2019, Revised 8 June 2020, Accepted 11 July 2020, Available online 16 July 2020, Version of Record 30 July 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113744