Comprehensive smartphone image dataset for bean and cowpea plant leaf disease detection and freshness assessment from Bangladesh vegetable fields

Abstract

Agriculture greatly impacts Bangladesh's economy, and vegetable cultivation plays a significant role in Agriculture by providing nourishment, and food security as well as improving the economy. The necessity of food production is growing similarly to the population growth. The farmers of Bangladesh are working hard to meet this need for food production and to gain yields. However, every year the farmers face a significant amount of loss in production due to the attack of different diseases and viruses due to the lack to technological development. The reason behind most of these losses is the lack of knowledge about diseases and being unable to detect the diseases early. Therefore, the early detection of plant disease is significant in balancing the country's economy and preventing undesirable losses. To bring a solution to this problem our dataset provides a total of 4467 images of Beans and Cowpeas leaf images which include different disease classes and fresh leaves. The dataset comprises 2,273 images of Bean and 2,194 images of Cowpea plants where each plant provides 4 classes of different disease along with the healthy leaves. This dataset will assist researchers in identifying plant diseases and farmers as well as contribute to the economy of the country.

Plant phenotyping relevance

豆類葉の画像から病害状態を推定する画像データセットが研究の中心であり、植物病害表現型のデータ資源として収録対象です。

Code and data availability

The paper is a Data in Brief article describing a smartphone image dataset of bean and cowpea leaf disease/freshness. The authors' own dataset is publicly deposited on Mendeley Data with an explicit direct URL and DOI, making it a paper-specific, publicly actionable asset. The Kaggle bean disease dataset is cited prior