Grayscale-inversion and rotation invariant image description with sorted LBP features

作者：

Highlights：

• We present a generic histogram sorting method to preserve the distribution information of LBP codes and their complements.

• We develop pairwise sorted LBP descriptors and fully sorted LBP descriptors.

• We propose a pyramid image representation which is invariant to grayscale inversion and image rotation.

• We contribute a new GII (grayscale-inversion images) database.

摘要

•We present a generic histogram sorting method to preserve the distribution information of LBP codes and their complements.•We develop pairwise sorted LBP descriptors and fully sorted LBP descriptors.•We propose a pyramid image representation which is invariant to grayscale inversion and image rotation.•We contribute a new GII (grayscale-inversion images) database.

论文关键词：Image feature,Illumination,Rotation,Invariance,Local binary pattern,Texture classification

论文评审过程：Received 10 February 2021, Revised 25 June 2021, Accepted 10 September 2021, Available online 17 September 2021, Version of Record 23 September 2021.

论文官网地址：https://doi.org/10.1016/j.image.2021.116491