ABSTRACT
This article presents the chili and onion leaf (COLD) dataset, which focuses on the leaves of chili and onion plants, scientifically known as Allium cepa and capsicum. The presence of various diseases such as Purple blotch, Stemphylium leaf blight, Colletotrichum leaf blight, and Iris yellow spot virus in onions, as well as Cercospora leaf spot, powdery mildew, Murda complex syndrome, and nutrition deficiency in chili, have had a significant negative effect on onion and chili production. As a consequence, farmers have incurred financial losses. Computer vision and image-processing algorithms have been widely used in recent years for a range of applications, such as diagnosing and categorizing plant leaf diseases. In this paper we introduced a detailed chilli and onion leaf dataset gathered from Chilwadigi village with varying climatic conditions in Karnataka. The dataset contains a variety of chili and onion leaf categories carefully selected to tackle the complex challenges of categorizing leaf images taken in natural environments. Dealing with challenges such as subtle inter-class similarities, changes in lighting, and differences in background conditions like different foliage arrangements and varying light levels. We carefully documented chilli and onion leaves from various angles using high resolution camera to create a diverse and reliable dataset. The dataset on chilli leaves is set to be a valuable resource for enhancing computer vision algorithms, from traditional deep learning models to cutting-edge vision transformer architectures. This will help in creating advanced image recognition systems specifically designed for identifying chilli plants. By making this dataset publicly accessible, our goal is to empower researchers to develop new computer vision techniques to tackle the unique challenges of chilli and onion leaf recognition. You can access the dataset for free at the following DOI number: http://doi.org/10.17632/7nxxn4gj5s.3 and http://doi.org/10.17632/tf9dtfz9m6.3.
ABSTRACT
The use of machine learning is rapidly expanding across many industries, including agriculture and the IT sector. However, data is essential for machine learning models, and a substantial amount of data is required prior to training a model. We have collected data of groundnut plant leaves in the form of digital photographs taken in the Koppal (Karnataka, India) area with the assistance of a pathologist in natural settings. Images of leaves are categorized into six distinct groups according to their condition. Collected images are pre-processed and the processed images of groundnut leaves are kept in 6 folders as: the "healthy leaves" folder with 1871 images, the "early leaf spot" folder with 1731 images, the "late leaf spot" folder with 1896 images, the "Nutrition deficiency" folder with 1665 images, the "rust" folder with 1724 images, and the "early rust" folder with 1474 images. The total number of images in the dataset is 10361. This dataset will be useful to train and validate deep learning and machine learning algorithms for groundnut leaf disease classification and recognition. Disease detection in plants is crucial for limiting crop losses and our dataset will help disease detection in groundnut plants. This dataset is freely accessible to public at https://data.mendeley.com/datasets/22p2vcbxfk/3 and at https://doi.org/10.17632/22p2vcbxfk.3.
