SimpliScopeX: Enhanced Deep Learning Model for Identification of Microscopic Image of Simplicia Fragments of Medicinal Plant Leaves

Abstract

As the "Back to Nature" trend progresses, people are switching from chemical medicine to herbal medicine or traditional medicine derived from nature. One form of traditional medicine is the simplicia of medicinal plant leaves. The authenticity of dried simplicia powder of medicinal plants can be determined through a microscopic test by looking at the identifier fragments. However, this remains difficult for humans to identify due to the need for more information on standard references. The dataset from microscopic images of simplicia fragments of medicinal plant leaves still needs to be improved. In addition, manual matching of microscopic test results with standard reference books requires quite a long time. It allows for human error, so it is necessary to apply artificial intelligence that can assist researchers in quickly and accurately predicting the species of medicinal plants and their fragments based on microscopic images. Deep learning performance has shown promising results in computer vision in recent years. Inspired by sophisticated deep learning techniques, the proposed work presents a deep learning method to identify and classify images of microscopic fragments of simple medicinal plants and their enhanced fragments using data augmentation techniques, modified EfficientNetB0 architecture, and the use of the ReduceLROnPlateau function in the training process, which is referred to as "SimpliScopeX". The SimpliScopeX model can also automatically extract microscopic image features of simplicia fragments of medicinal plant leaves. Experimental results using the new dataset show that our proposed model can produce the highest accuracy value of 80.25% for the test data for microscopic image problems of medicinal leaf simplicia. The implications of this research are petrified in the pharmaceutical world in fast and accurate microscopic identification.