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

•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.