Medicinal plants have been used to treat diseases since ancient times. Plants used as raw materials for herbal medicine are known as medicinal plants [2]. The U. S. Forest Service estimates that 40% of pharmaceutical drugs in the Western world are derived from plants [1]. Seven thousand medical compounds are derived from plants in the modern pharmacopeia. Herbal medicine combines traditional empirical knowledge with modern science [2]. A medicinal plant is considered an important source of prevention against various diseases [2]. The essential medicine component is extracted from different parts of the plants [8]. In underdeveloped countries, people use medicinal plants as a substitute for medicine. There are various species of plants in the world. Herbs are one of them, which are of different shapes, colors, and leaves [5]. It is difficult for ordinary people to recognize these species of herbs. People use more than 50000 plants in the world for medicinal purposes. There are 8000 medicinal plants in India with evidence of medicinal properties [7]. Automatic classification of these plant species is important because it requires intensive domain knowledge to manually classify the proper species. Machine learning techniques are extensively used in classifying medicinal plant species from photographs, which is challenging but intriguing to academics. Artificial Neural Network classifiers' effective performance depends on the quality of the image dataset [4]. This article represents a medicinal plant dataset: an image dataset of ten different Bangladeshi plant species. Images of medicinal plant leaves were from various gardens, including the Pharmacy Garden at Khwaja Yunus Ali University and the Khwaja Yunus Ali Medical College & Hospital in Sirajganj, Bangladesh. Images were collected by taking pictures with high-resolution mobile phone cameras. Ten medicinal species, 500 images per species are included in the data set, namely, Nayantara (Catharanthus roseus), Pathor kuchi (Kalanchoe pinnata), Gynura procumbens (Longevity spinach), Bohera (Terminalia bellirica), Haritaki (Terminalia chebula), Thankuni (Centella asiatica), Neem (Azadirachta indica), Tulsi (Ocimum tenniflorum), Lemon grass (Cymbopogon citratus), and Devil backbone (Euphorbia tithymaloides). This dataset will benefit researchers applying machine learning and computer vision algorithms in several ways. For example, training and evaluation of machine learning models with this well-curated high-quality dataset, development of new computer vision algorithms, automatic medicinal plant identification in the field of botany and pharmacology for drug discovery and conservation, and data augmentation. Overall, this medicinal plant image dataset can provide researchers in the field of machine learning and computer vision with a valuable resource to develop and evaluate algorithms for plant phenotyping, disease detection, plant identification, drug development, and other tasks related to medicinal plants.
Keywords: DenseNet201; Feature visualization; Image classification; Image processing; Medicinal plant.
© 2023 The Author(s).