A novel approach to navigate the taxonomic hierarchy to address the Open-World Scenarios in Medicinal Plant Classification

TL;DR

This paper introduces a hierarchical classification method for medicinal plants that effectively identifies known and unknown species using DenseNet121, Multi-Scale Self-Attention, and cascaded classifiers, achieving high accuracy and efficiency.

Contribution

It presents a novel hierarchical classification approach integrating MSSA and cascaded classifiers, addressing unknown species detection in medicinal plant taxonomy.

Findings

Achieved 83.36% accuracy for unknown species at the phylum level.

Model size is four times smaller than existing methods.

Effective in real-world applications with background artifacts.

Abstract

In this article, we propose a novel approach for plant hierarchical taxonomy classification by posing the problem as an open class problem. It is observed that existing methods for medicinal plant classification often fail to perform hierarchical classification and accurately identifying unknown species, limiting their effectiveness in comprehensive plant taxonomy classification. Thus we address the problem of unknown species classification by assigning it best hierarchical labels. We propose a novel method, which integrates DenseNet121, Multi-Scale Self-Attention (MSSA) and cascaded classifiers for hierarchical classification. The approach systematically categorizes medicinal plants at multiple taxonomic levels, from phylum to species, ensuring detailed and precise classification. Using multi scale space attention, the model captures both local and global contextual information from the images, improving the distinction between similar species and the identification of new ones. It uses attention scores to focus on important features across multiple scales. The proposed method provides a solution for hierarchical classification, showcasing superior performance in identifying both known and unknown species. The model was tested on two state-of-art datasets with and without background artifacts and so that it can be deployed to tackle real word application. We used unknown species for testing our model. For unknown species the model achieved an average accuracy of 83.36%, 78.30%, 60.34% and 43.32% for predicting correct phylum, class, order and family respectively. Our proposed model size is almost four times less than the existing state of the art methods making it easily deploy able in real world application.