Unsupervised manifold learning through reciprocal kNN graph and Connected Components for image retrieval tasks

作者：

Highlights：

• Presentation of an unsupervised manifold learning method based on Reciprocal kNN Graphs and Connected Components.

• Discussion about the use of the method for distance learning in order to improve the effectiveness of image retrieval tasks.

• Discussion about contributions, algorithm’s efficiency and progresses in front of other unsupervised approaches.

• Experimental evaluation considering various datasets, several features and comparison with state-of-the-art methods.

摘要

•Presentation of an unsupervised manifold learning method based on Reciprocal kNN Graphs and Connected Components.•Discussion about the use of the method for distance learning in order to improve the effectiveness of image retrieval tasks.•Discussion about contributions, algorithm’s efficiency and progresses in front of other unsupervised approaches.•Experimental evaluation considering various datasets, several features and comparison with state-of-the-art methods.

论文关键词：Content-based image retrieval,Unsupervised manifold learning,Reciprocal kNN graph,Connected components

论文评审过程：Received 8 November 2016, Revised 10 March 2017, Accepted 13 May 2017, Available online 13 May 2017, Version of Record 21 November 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.05.009