Sazzad Sadia, Rajbongshi Aditya, Shakil Rashiduzzaman, Akter Bonna, Kaiser M Shamim
Department of Computer Science and Engineering, National Institute of Textile Engineering and Research, Dhaka, Bangladesh.
Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh.
Data Brief. 2022 Aug 2;44:108497. doi: 10.1016/j.dib.2022.108497. eCollection 2022 Oct.
For the welfare of self-development and the country's economic evolution, people invest their youth and money in different cultivation and sustainable production business sectors. The crops or fruits get all the attention for this purpose, but currently, the commercial cultivation of flowers is becoming a numerous beneficial investment. As a consequence, the rose() is one of the most beautiful and commercially demanding flowers among different flowers. However, insecticide resistance is considered one of the lion's share issues facing agricultural production of roses by decreasing plants' growth and the quality as well as the quantity of healthy-looking flowers. Apart from this, due to different natural and environmental issues, rose's quality and production level are losing their fame. Additionally, the cultivators of this sector are not educated enough to identify the initial affection of different diseases of leaves with beard eyes. Besides, the lack of communication skills to consult with an agriculturist timely turns the situation worst more than the estimation of the production. With this concern, early detection of diseases that affected different parts of roses, such as leaves, is crucial. Recently, image processing techniques and machine learning classifiers have been primarily applied to recognize multiple diseases. This article presents an extensive dataset of rose leaves images, both diseases affected and diseases free are classified into three classes (Blackspot, Downy Mildew, and Fresh Leaf). The dataset is composed of the collected images which were captured during the seasonal time of diseases affection with the consultation of a domain expert and the dataset is accessible at https://data.mendeley.com/datasets/7z67nyc57w/2.
为了自身发展和国家经济发展的福祉，人们将青春和金钱投入到不同的种植和可持续生产商业领域。为此，农作物或水果备受关注，但目前花卉的商业种植正成为一项众多益处的投资。因此，玫瑰是不同花卉中最美丽且商业需求最大的花卉之一。然而，抗药性被认为是玫瑰农业生产面临的主要问题之一，它会降低植物的生长、健康花朵的质量和数量。除此之外，由于不同的自然和环境问题，玫瑰的品质和产量正在失去声誉。此外，该领域的种植者没有足够的知识来通过肉眼识别叶片不同病害的初期症状。此外，缺乏及时咨询农学家的沟通技巧，使得情况比产量预估更糟。出于这种担忧，早期检测影响玫瑰不同部位（如叶片）的病害至关重要。最近，图像处理技术和机器学习分类器已主要应用于识别多种病害。本文展示了一个玫瑰叶片图像的广泛数据集，受病害影响和未受病害影响的图像被分为三类（黑斑病、霜霉病和新鲜叶片）。该数据集由在病害高发季节收集的图像组成，并经过领域专家的咨询，该数据集可在https://data.mendeley.com/datasets/7z67nyc57w/2获取。
