First appeared at https://data.mendeley.com/datasets/4gkcyxjyss/1
‘SorghumWeedDataset_Classification’ is created to address real-time weed challenges and encourage weed research using computer vision applications.
‘SorghumWeedDataset_Classification’ is a crop-weed research dataset with 4312 data samples, which can be used for image classification. Sorghum samplings (Class 0), Grasses (Class 1), and Broad-leaf weeds (Class 2) are the three research objects focused during this data acquisition process. This dataset contains 1404 samples of sorghum samplings, 1467 samples of grasses, and 1441 samples of broadleaved weeds. The TVT (Train: Validate: Test) ratio is set as 7:2:1 to split the data samples into training, validation, and testing. Data samples with class labels are provided herewith.
To record a rich set of information on the research objects, a state-of-the-art instrument - Canon EOS 80D – a Digital Single Lens Reflex (DSLR) camera with a sensor type of 22.3mm x 14.9 mm CMOS is used.
Each data sample is an RGB image represented in JPEG format with 6000 × 4000 pixels making an average size of 13MB each. All data samples are re-sized to 224 × 224 pixels without information loss to reduce the computation complexity.
This dataset emphasizes the early stages of crop growth to meet the challenges faced during the ‘Critical period of weed competition’. Data samples are captured from agriculture fields that follow both uniform crop spacing and random crop spacing.
Data is acquired during April and May 2023. To generalize the dataset, acquisition is done in various light and weather conditions with varying distances.
Data is acquired from Sri Ramaswamy Memorial (SRM) Care Farm, Chengalpattu district, Tamil Nadu, India. To the best of our knowledge, ‘SorghumWeedDataset_Classification’ is the first open-access crop-weed research dataset from Indian fields for classification that deals with weed issues in uniform and random crop-spacing fields.
The expected outcome of this dataset will be an Artificial Intelligence (AI) model that predicts the correct class of a particular data sample.
The data article in the journal "Data in Brief" provides a thorough explanation of the dataset and the data acquisition procedure. It can be accessed at https://www.sciencedirect.com/science/article/pii/S2352340923009678
If you find this dataset helpful and use it in your work, kindly cite this dataset using “Michael, Justina; M, Thenmozhi (2023), “SorghumWeedDataset_Classification”, Mendeley Data, V1, doi: 10.17632/4gkcyxjyss.1”
- Justina Michael. J
Google Scholar: https://scholar.google.com/citations?user=pEEzO14AAAAJ&hl=en&oi=ao
ORCID: https://orcid.org/0000-0001-8072-3230 - Dr. M. Thenmozhi
Google Scholar: https://scholar.google.com/citations?user=Es49w08AAAAJ&hl=en&oi=ao
ORCID: https://orcid.org/0000-0002-8064-5938