Computer Vision for Agriculture
Building robust, field-deployable models for crop-disease detection that work under real-world variability in lighting, occlusion and capture quality.
Research statement & programme
Abstract
- Field
- Computer Vision · Machine Learning
- Domains
- Agriculture · Healthcare
- Status
- Seeking MSc & research roles
- Publications
- 1 · Data in Brief (2025)
- Open to
- Collaboration & supervision
My research sits at the intersection of computer vision, machine learning and their application to high-stakes, data-scarce domains — principally agriculture and healthcare. I am interested in models that remain robust under real-world variability, that are interpretable enough to be trusted by domain experts, and that are released alongside open, reproducible datasets. I believe the bottleneck in applied AI is rarely the architecture; it is the quality, availability and honesty of the data and evaluation around it. My work therefore pairs model development with careful dataset construction and reproducible baselines.
Research Interests
Trustworthy Healthcare AI
Developing interpretable models for medical imaging and health data where reliability and explainability are prerequisites for adoption.
Areas of focus
- 01Machine Learning
Designing and training models that learn from data — from classical methods to modern deep architectures.
- 02Computer Vision
Teaching machines to interpret images — classification, detection and segmentation for real-world problems.
- 03Healthcare AI
Applying machine learning to medical and health data to support diagnosis and decision-making.
- 04Agricultural AI
Precision agriculture through computer vision — crop-disease detection and yield optimization.
- 05Human-Computer Interaction
Crafting interfaces and interactions that are intuitive, accessible and genuinely human-centered.
- 06Data Science
Turning raw data into insight through statistical analysis, visualization and reproducible pipelines.
Current Work
Eggplant Leaf Disease Classification
Building on our published six-class dataset of 4,089 eggplant-leaf images to develop stronger augmentation strategies and transfer-learning baselines that improve classification accuracy on harder disease classes such as mosaic virus and wilt.
Selected Publications
- [1]
Shakib Howlader, Md. Sabbir Ahamed, Mayen Uddin Mojumdar, Sheak Rashed Haider Noori, Shah Md Tanvir Siddiquee, Narayan Ranjan Chakraborty. “A comprehensive image dataset for the identification of eggplant leaf diseases and computer vision applications.” Data in Brief, 2025.
This dataset comprises 4,089 high-resolution images of eggplant (Solanum melongena) leaves, systematically categorized into six distinct classes: healthy leaves and five disease types — insect pest disease, leaf spot disease, mosaic virus disease, white mold disease, and wilt disease. The images were captured using smartphone cameras against consistent white backgrounds under varying lighting conditions across multiple geographic locations, then subjected to thorough manual labelling and preprocessing to ensure accuracy and consistency. The resource is particularly suitable for applications in plant pathology, precision agriculture, and disease forecasting, where timely and accurate diagnosis is crucial. Freely available for academic research, the dataset aims to advance automated disease-detection systems and sustainable farming practices.
Datasets
Eggplant Leaf Disease Dataset — 4,089 images, 6 classes
An openly available, manually labelled image dataset of eggplant leaves spanning healthy specimens and five disease types (insect pest, leaf spot, mosaic virus, white mold, wilt), captured across multiple locations for reproducible machine-learning research.
Past Work
Eggplant Leaf Disease Dataset (Data in Brief, 2025)
Led the construction and open release of a 4,089-image, six-class eggplant-leaf dataset captured under varied field and lighting conditions — manually labelled and preprocessed for reproducible computer-vision research. Published in Elsevier's Data in Brief.
Future Directions
Multimodal Crop-Health Monitoring
Combining imagery with environmental and sensor data for earlier, more accurate detection of plant stress — a direction I aim to pursue at MSc level.
Collaboration
Open to Collaboration
Actively seeking research collaborations and MSc supervision in computer vision, agricultural AI and healthcare AI.
I am actively seeking MSc supervision and research collaborations in computer vision, agricultural AI and healthcare AI.
Get in touch →