A sequential search-space shrinking using CNN transfer learning and a Radon projection pool for medical image retrieval

作者：

Highlights：

• Propose a two-step hierarchical shrinking search space when a descriptoris used.

• Transfer learning via CNNs is utilized for the first stage shrinking.

• A selection pool using Radon transform is created for further shrinking.

• Difference between two orthogonal Radon projections is considered in the pool.

• A state-of-the-art result is achieved on the IRMA challenging dataset.

摘要

•Propose a two-step hierarchical shrinking search space when a descriptoris used.•Transfer learning via CNNs is utilized for the first stage shrinking.•A selection pool using Radon transform is created for further shrinking.•Difference between two orthogonal Radon projections is considered in the pool.•A state-of-the-art result is achieved on the IRMA challenging dataset.

论文关键词：Content-based image retrieval,CBIR,Medical imaging,Deep learning,Radon

论文评审过程：Received 29 July 2017, Revised 10 January 2018, Accepted 31 January 2018, Available online 6 February 2018, Version of Record 16 February 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.01.056