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 drastically
vary among the different genera of the same subspecies. Computer
Vision and Machine Learning research areas made possible the
creation of different classifiers trained to assist in species plant
recognition based on digital images. However, the success of the
training of a classification model is directly linked to the quality
and adequacy of the dataset used. For the classification of Acer
Palmatum plants, datasets composed of samples regarding the different
varieties within this genus were not identified. Thus, in this
paper, we proposed the creation of a new dataset and of a classifier
to support the identification of distinct plant genera of the subspecies
Acer Palmatum. We believe that our proposal aggregates
relevant information not currently available, and will encourage
further work aimed at automatically classifying between genera of
some plant species which task is considered non-trivial even for
experienced growers.