Lentil plant disease and quality assessment: A detailed dataset of high-resolution images for deep learning research

The Lentil, a vital legume globally cultivated, faces significant challenges from diseases like ascochyta blight, lentil rust, and powdery mildew. Ensuring optimal harvest timing and effectively discerning healthy and diseased lentil plants are crucial for maintaining crop quality and economic viability, particularly in regions such as Bangladesh. This paper introduces a comprehensive dataset comprising high-resolution images of lentil plants gathered meticulously over four months from diverse locations across Bangladesh, under expert supervision. The dataset aims to support the development of machine-learning models for precise disease detection and quality assessment in lentil cultivation. Potential applications include enhancing the accuracy of quality evaluation, and improving packaging processes, thereby enhancing overall lentil production efficiency. Agricultural researchers can utilize this dataset to advance applications of computer vision and deep learning in managing crop diseases and enhancing yield outcomes. The dataset's creation involved collaboration with domain experts to ensure its relevance and reliability for agricultural research. By leveraging this dataset, researchers can explore innovative approaches to tackle challenges in lentil farming, contributing to sustainable agricultural practices and food security. Moreover, the dataset serves as a valuable resource for training and testing machine learning algorithms tailored to agricultural settings, facilitating advancements in automated agricultural technologies. Ultimately, this initiative aims to empower stakeholders in the lentil industry with tools to mitigate disease impact and optimize production practices, paving the way for more resilient and efficient agricultural systems globally<i>.</i>