A visual dataset for recognition of rice varieties

Abstract

This article presents a comprehensive dataset sourced from various markets across Bangladesh, highlighting 20 distinct rice varieties predominantly consumed locally. The dataset encompasses a diverse range of rice strains, including Subol Lota, Bashmoti (Deshi), Ganjiya, Shampakatari, Sugandhi Katarivog, BR-28, BR-29, Paijam, Bashful, Lal Aush, BR-Jirashail, Gutisharna, Birui, Najirshail, Pahari Birui, Polao (Katari), Polao (Chinigura), Amon, Shorna-5, and Lal Binni. Using a smartphone camera, low-resolution images capturing the essence of each rice variety were meticulously obtained, resulting in a total of 4,730 images with a non-uniform distribution. The dataset also includes augmented data, totaling 23,650 images. This precisely curated dataset holds significant promise and utility, showcasing diverse attributes, including the unique representation of 20 rice varieties, each characterized by distinct colors, sizes, and potential applications within the agricultural sector.

Keywords

• Image classification
• Rice varieties
• Computer vision
• Deep learning