Spatial-Structure Siamese Network for Plant Identification

Abstract

Plant identification is now attracting considerable attention due to its important applications in agriculture automation and ecosystems. Recently, deep learning-based plant identification methods have drawn increasing interest and shown favorable performance. However, existing methods do not consider plant spatial structure and their similarities explicitly. In this paper, we propose a robust spatial-structure siamese network (3SN) for plant identification, which has the following advantages: (1) It models the spatial structure of a plant by recurrent neural networks exploiting their capability to capture long-range dependencies among sequential data, which enables it to capture even a slight difference between a specific plant and distractors. (2) The plant similarity modeling is achieved effectively by a siamese network with large numbers of image pairs. In this way, the plant classification task and siamese learning task are learned jointly in a unified framework, where both can enhance and complement each other. Extensive experimental results show that the proposed 3SN method outperforms the state-of-the-art methods consistently.