An End-to-End-Based Low Dimensional Binary Embedding for Chrysanthemum Phenotypic Petal Similarity Evaluation

Abstract

Plant phenotyping is widely used to identify the genotype differences and the environmental conditions of plants. These pieces of information can be gathered by various sensors conveniently and easily. The similarity evaluation of phenotypic data is essential for category classifications and stress sensitivity analysis of plants. Chrysanthemum is a flower with great varieties and petal types. The similarity evaluation of chrysanthemum flowers plays a key role in the phenotypic research. For improving the performance and effectiveness of phenotypic similarity evaluation of high-throughput chrysanthemum flower images, this paper proposes an end-to-end based low dimensional binary embedding framework by using deep learning and hash encoding approaches. Within this framework, compact binary codes are learned by deep convolutional neural networks. Firstly, features of chrysanthemum images are extracted by deep neural networks, then a binary layer is embedded for converting the features into lower dimensional bit codes. Finally, the phenotypic similarity of the chrysanthemum flower is evaluated in Hamming space with the binary codes. Extensive experiments are conducted and the results show that the performance and effectiveness of similarity evaluations are improved greatly. In summary, our research provides an end-to-end pipeline for the similarity evaluation of chrysanthemum petal phenotypes, and the proposed method is practically applicable to the high-throughput similarity evaluation. The proposed method can be used as a foundation for the in-depth research on chrysanthemum flower petals as well.