RSILC: Rotation- and Scale-Invariant, Line-based Color-aware descriptor
作者：
Highlights：
• A new rotation- and scale-invariant line-based color-aware descriptor is introduced.
• The descriptor captures both local (texture, color) and global (inter-line spatial) information.
• Experiments show that proposed descriptor is robust to rotation, scale, and illumination.
• The descriptor is compared to the well-known descriptors.
• The proposed descriptor is more accurate on matching line-rich objects such as faces.
摘要
•A new rotation- and scale-invariant line-based color-aware descriptor is introduced.•The descriptor captures both local (texture, color) and global (inter-line spatial) information.•Experiments show that proposed descriptor is robust to rotation, scale, and illumination.•The descriptor is compared to the well-known descriptors.•The proposed descriptor is more accurate on matching line-rich objects such as faces.
论文关键词：Image descriptor,Local features,Spatial features,Rotation invariance,Scale invariance,Color aware
论文评审过程：Received 26 August 2014, Revised 29 April 2015, Accepted 29 June 2015, Available online 15 July 2015, Version of Record 7 August 2015.
论文官网地址：https://doi.org/10.1016/j.imavis.2015.06.010
