Symmetric Binary Tree Based Co-occurrence Texture Pattern Mining for Fine-grained Plant Leaf Image Retrieval

作者：

Highlights：

• This work focuses on leaf image retrieval in cultivar level known as a very fine-grained image recognition problem.

• Symmetric binary tree (SBT) is designed for mining co-occurrence texture patterns.

• A novel feature fusion scheme, named K-NN Based Handcrafted and Deep Features Fusion, is proposed.

• The effectiveness of the proposed method has been validated on the soybean cultivar leaf dataset and peanut cultivar leaf dataset.

摘要

•This work focuses on leaf image retrieval in cultivar level known as a very fine-grained image recognition problem.•Symmetric binary tree (SBT) is designed for mining co-occurrence texture patterns.•A novel feature fusion scheme, named K-NN Based Handcrafted and Deep Features Fusion, is proposed.•The effectiveness of the proposed method has been validated on the soybean cultivar leaf dataset and peanut cultivar leaf dataset.

论文关键词：Leaf image pattern,Species recognition,Fine-grained image recognition,Feature fusion,Image retrieval

论文评审过程：Received 11 October 2021, Revised 22 March 2022, Accepted 30 April 2022, Available online 3 May 2022, Version of Record 9 May 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108769