Assessment of mobile phone applications feasibility on plant recognition: comparison with Google Lens AR-app

Abstract

The paper is devoted to systemizing all mobile applications used during the STEM-classes and can be used to identify plants. There are 10 mobile applications that are plant identifiers worldwide. These applications can be divided into three groups, such as plant identifiers that can analyze photos, plant classification provides the possibility to identify plants manually, plants-care apps that remind water of the plant, or change the soil. In this work, mobile apps such as Flora Incognita, PlantNet, PlantSnap, PictureThis, LeafSnap, Seek, PlantNet were analyzed for usability parameters and accuracy of identification. To provide usability analysis, a survey of experts of digital education on installation simplicity, level of friendliness of the interface, and correctness of picture processing. It is proved that Flora Incognita and PlantNet are the most usable and the most informative interface from plant identification apps. However, they were characterized by significantly lower accuracy compared to Google Lens results. Further comparison of the usability of applications that have been tested in the article with Google Lens, proves that Google Lens characterize by better usability and therefore, Google Lens is the most recommended app to use to provide plant identification during biology classes.