Classification of Orchid Types using Random Forest Method with HOG Features

Abstract

Orchids are one of the Indonesian people's most widely cultivated ornamental plants. Orchids are a family of
plants in the Orchidaceae family that includes more than 700 genera and around 28,000 individual species. In terms of
plant morphology, orchids can be distinguished based on the morphology of flowers, leaves, fruits, stems, and roots.
Orchid leaves have their characteristics for each type of orchid, such as long, round, or lanceolate. All orchids have leaf
veins that are parallel to the leaves. This makes it difficult to identify the type of orchid flower, especially for laypeopl e
who are new to orchid cultivation and do not yet know the characteristics of various kinds of orchids. The individual
shapes of orchid leaves can be classified using Random Forest and Histogram of Oriented Gradients (HOG). In this
study, three types of orchids that are currently popular with orchid lovers were used, namely Cattleya, Phalaenopsis, and
Vanda orchids taken from public data. The accuracy of this method in classifying orchid types based on leaf morphology
can be measured using a confusion matrix that measures accuracy, precision, recall, and F1-score. The test results show
that this method successfully achieved an accuracy of 98%, with an average precision, recall, and F1-score of 0.98 each.
These findings indicate that the model built can classify orchid species with a high level of accuracy based on leaf
morphology.