Texture descriptors for representing feature vectors

作者：

Highlights：

• Combining matrix descriptors with vector features improves classifier performance.

• 1D feature vectors treated as trees can be used to build matrix representations.

• Features extracted from matrix representation of input vectors are generalizable to many problems.

摘要

•Combining matrix descriptors with vector features improves classifier performance.•1D feature vectors treated as trees can be used to build matrix representations.•Features extracted from matrix representation of input vectors are generalizable to many problems.

论文关键词：Two-dimensional representation,Medical dataset,Ensemble of classifiers,General-purpose classifier

论文评审过程：Received 4 April 2018, Revised 26 October 2018, Accepted 29 December 2018, Available online 31 December 2018, Version of Record 8 January 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.12.052