Semantic Guided Interactive Image Retrieval for plant identification

作者：

Highlights：

• Reduction of semantic gap between image representation and its visual content.

• A graph-based approach combining low-level features and knowledge from ontologies.

• A semantic guided interactive retrieval approach for plant identification.

• A systematic botany ontology, which describes and conceptualizes Angiosperm families.

• Experiments achieved high effectiveness on image retrieval and identification tasks.

摘要

•Reduction of semantic gap between image representation and its visual content.•A graph-based approach combining low-level features and knowledge from ontologies.•A semantic guided interactive retrieval approach for plant identification.•A systematic botany ontology, which describes and conceptualizes Angiosperm families.•Experiments achieved high effectiveness on image retrieval and identification tasks.

论文关键词：Interactive image retrieval,Unsupervised learning,Semantic gap,Ontology

论文评审过程：Received 1 March 2017, Revised 18 August 2017, Accepted 19 August 2017, Available online 21 August 2017, Version of Record 5 October 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.08.035