Visual orientation inhomogeneity based scale-invariant feature transform

作者：

Highlights：

• Provide the evidence of existence of the least important visual orientation.

• Novel algorithm with high efficiency is proposed to detect and describe local feature.

• Better performance for detection and matching, comparable performance for recognition.

摘要

•Provide the evidence of existence of the least important visual orientation.•Novel algorithm with high efficiency is proposed to detect and describe local feature.•Better performance for detection and matching, comparable performance for recognition.

论文关键词：Orientation inhomogeneity,Real-world distribution,Scale-invariant feature transform,Least discriminability

论文评审过程：Available online 16 January 2015.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.01.012