A Multi-District Field-Acquired Sugarcane Disease Image Dataset From Assam For AI-Based Crop Disease Detection

Authors

  • Ankita Goyal Agarwala Research Scholar, Department of IT, Gauhati University, Guwahati, Assam-781014
  • Mirzanur Rahman Associate Professor, Department of IT, Gauhati University, Guwahati, Assam-781014
  • Jyotismita Das B. Tech (CSE) 8th Semester, Department of CSE, The Assam Royal Global University, Guwahati, Assam-781035
  • Yash Pareek B. Tech (CSE) 8th Semester, Department of CSE, The Assam Royal Global University, Guwahati, Assam-781035
  • Manash Choudhury B. Tech (CSE) 8th Semester, Department of CSE, The Assam Royal Global University, Guwahati, Assam-781035

DOI:

https://doi.org/10.29284/bc4sqh63

Keywords:

Sugarcane disease; Image dataset; Deep learning; Precision agriculture; Assam.

Abstract

Sugarcane is a major agricultural crop in Assam, India, where disease outbreaks significantly affect yield and farmer income. The development of automated disease detection systems requires region-specific, high-quality datasets. This study presents a curated dataset comprising 5,769 field-acquired sugarcane leaf images collected from multiple districts of Assam under natural environmental conditions. The dataset contains 5,769 field-acquired images categorized into nine classes representing eight disease types and healthy plants.

Images were captured following standardized acquisition protocols and annotated through a structured labeling process. Quality control measures were applied to ensure clarity and class consistency. To evaluate dataset robustness, benchmark experiments were conducted using established convolutional neural network architectures. Performance metrics including accuracy, precision, recall, and F1-score are reported.


The dataset is made publicly available to support reproducible research and AI-driven crop disease monitoring systems tailored to humid agro-climatic regions.

References

[1] Oerke, E.-C., 2006. Crop losses to pests. Journal of Agricultural Science, 144(1), 31–43.

[2] Mohanty, S.P., Hughes, D.P., Salathé, M., 2016. Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419.

[3] Sladojevic, S., Arsenovic, M., Anderla, A., Culibrk, D., Stefanovic, D., 2016. Deep neural networks based recognition of plant diseases by leaf image classification. Computational Intelligence and Neuroscience, 2016, 3289801.

[4] Barbedo, J.G.A., 2018. Factors influencing the use of deep learning for plant disease recognition. Biosystems Engineering, 172, 84–91.

[5] Vikaspedia: Sugarcane Diseases and Symptoms. www. vikaspedia.in, https://vikaspedia.in/agriculture/crop-production/integrated-pest-managment/ipm-for-commercial-crops/ipm-strategies-for-sugarcane/sugarcane-diseases-and-symptoms (accessed 13 May 2024).

[6] Sarmah, C. and Sarma, P., A dataset of Sattriya dance: Classical dance of Assam. Data in Brief, 52, p (2024).109878. https://doi.org/10.1016/j.dib.2023.109878

[7] Thite, S., Suryawanshi, Y., Patil, K., Chumchu, P., 2024.Sugarcane leaf dataset: A dataset for disease detection and classification. Data in Brief 53, 110268.

[8] Goyal Agarwala, Ankita; Rahman, Dr. Mirzanur; Sarwar Zaman, Dr Gaffar (2024), “Sugarcane Plant Disease Dataset of Assam”, Mendeley Data, V1, doi: 10.17632/x98kpjvxxg.1

Downloads

Published

2025-09-25

Issue

Section

Articles

How to Cite

[1]
A. G. Agarwala, M. Rahman, J. Das, Y. Pareek, and M. Choudhury, “A Multi-District Field-Acquired Sugarcane Disease Image Dataset From Assam For AI-Based Crop Disease Detection”, IJASIS, pp. 635–644, Sep. 2025, doi: 10.29284/bc4sqh63.

Share