Abstract
In recent years, the method of plant leaf classification by deep learning has gradually become mature. However, training a leaf classifier based on deep learning requires a large number of samples for supervised training. In this paper, a few-shot learning method based on the Siamese network framework is proposed to solve a leaf classification problem with a small sample size. First, the features of two different images are extracted by a parallel two-way convolutional neural network with weight sharing. Then, the network uses a loss function to learn the metric space, in which similar leaf samples are close to each other and different leaf samples are far away from each other. In addition, a spatial structure optimizer (SSO) method for constructing the metric space is proposed, which will help to improve the accuracy of leaf classification. Finally, a k-nearest neighbor (kNN) classifier is used to classify leaves in the learned metric space. The average classification accuracy is used as a performance measure. The open access Flavia, Swedish and Leafsnap datasets are used to evaluate the performance of the method. The experimental results show that the proposed method can achieve a high classification accuracy with a small size of supervised samples.
Highlights
Plants are widely distributed in the natural environment, participate in the material cycle of the ecosystem, and play an important role in protecting the earth’s ecosystem
As we can see from the table, all the methods improve the accuracy when the number of supervised samples increases, but the S-Inception method improves faster, because the generalization ability of the S-Inception structure is better, and the width of the structure makes it possible to extract more features when the number of samples increases
WORK In this paper, an improved convolutional neural network structure is proposed to solve the problem of leaf classification in the case of small samples, which is of great significance for solving the problem of sparse samples or various types of classification tasks
Summary
Plants are widely distributed in the natural environment, participate in the material cycle of the ecosystem, and play an important role in protecting the earth’s ecosystem. The conservation of plant species requires the ability to artificially classify their species, a skill that comes from intensive learning and experience [2]. It is almost impossible for ordinary people to identify traditional plant species, and even for practitioners who come into contact with plants every day, such as horticulturists, farmers and landscape architects have difficulty classifying plant species. This issue is called the taxonomic crisis in the field of related research [3]. Botanists believe that technological of plant image retrieval can greatly reduce the gap in plant classification skills of researchers from different fields [4]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
