Graph regularized nonnegative sparse coding using incoherent dictionary for approximate nearest neighbor search

作者：

Highlights：

• Graph Laplacian regularization is considered for improvement.

• Non-negativity constraints are adopted for enriching sparse codes.

• An iterative algorithm is proposed to learn incoherent dictionary.

• Interesting improvement is reaped without sacrificing query time.

摘要

•Graph Laplacian regularization is considered for improvement.•Non-negativity constraints are adopted for enriching sparse codes.•An iterative algorithm is proposed to learn incoherent dictionary.•Interesting improvement is reaped without sacrificing query time.

论文关键词：Nonnegative sparse coding,Incoherent dictionary learning,Laplacian regularization,Approximate nearest neighbor searching,Image retrieval

论文评审过程：Received 4 August 2016, Revised 13 January 2017, Accepted 30 April 2017, Available online 1 May 2017, Version of Record 12 May 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.04.030