Developing an automatic classifier of different plant genera of the subspecies Acer Palmatum

Abstract

Plant species identification is a task of interdisciplinary interest,desirable in many contexts, such as gardening, botanical research,and agriculture. For some plant species such as the Acer Palmatum,the characteristics of leaves, petioles, and trunks can drasticallyvary among the different genera of the same subspecies. ComputerVision and Machine Learning research areas made possible thecreation of different classifiers trained to assist in species plantrecognition based on digital images. However, the success of thetraining of a classification model is directly linked to the qualityand adequacy of the dataset used. For the classification of AcerPalmatum plants, datasets composed of samples regarding the differentvarieties within this genus were not identified. Thus, in thispaper, we proposed the creation of a new dataset and of a classifierto support the identification of distinct plant genera of the subspeciesAcer Palmatum. We believe that our proposal aggregatesrelevant information not currently available, and will encouragefurther work aimed at automatically classifying between genera ofsome plant species which task is considered non-trivial even forexperienced growers.