Plant systematics can be classified and recognized based on their reproductive system (flowers) and leaf morphology. Neural networks is one of the most popular machine learning algorithms for plant leaf classification. The commonly used neutral networks are artificial neural network (ANN), probabilistic neural network (PNN), convolutional neural network (CNN), k-nearest neighbor (KNN) and support vector machine (SVM), even some studies used combined techniques for accuracy improvement. The utilization of several varying preprocessing techniques, and characteristic parameters in feature extraction appeared to improve the performance of plant leaf classification. The findings of previous studies are critically compared in terms of their accuracy based on the applied neural network techniques. This paper aims to review and analyze the implementation and performance of various methodologies on plant classification. Each technique has its advantages and limitations in leaf pattern recognition. The quality of leaf images plays an important role, and therefore, a reliable source of leaf database must be used to establish the machine learning algorithm prior to leaf recognition and validation.
Labisia pumila is a precious herb in Southeast Asia that is traditionally used as a health supplement and has been extensively commercialized due to its claimed therapeutic properties in boosting a healthy female reproductive system. Indigenous people used these plants by boiling the leaves; however, in recent years it has been marketed as powdered or capsuled products. Accordingly, accuracy in determination of the authenticity of these modern herbal products has faced great challenges. Lack of authenticity is a public health risk because incorrectly used herbal species can cause adverse effects. Hence, any measures that may aid product authentication would be beneficial. Given the widespread use of Labisia herbal products, the current study focuses on authenticity testing via an integral approach of DNA barcoding and qualitative analysis using HPLC. This study successfully generated DNA reference barcodes (ITS2 and rbcL) for L.pumila var. alata and pumila. The DNA barcode that was generated was then used to identify species of Labisia pumila in herbal medicinal products, while HPLC was utilized to determine their quality. The findings through the synergistic approach (DNA barcode and HPLC) implemented in this study indicate the importance of both methods in providing the strong evidence required for the identification of true species and to examine the authenticity of such herbal medicinal products.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.