] MSU Dry Beans
Skip to main content
Michigan State Universitysite name

Dry Bean Dataset

Dry beans are an important agricultural product and source of nutrition. Ongoing research is seeking to develop new varieties with improved nutritional properties and resistance to insects, disease and drought, and at the same time maintaining or improving bean quality. An important quality measure is bean intactness after cooking and canning. Splits in the seed coats, such as those below, detract from bean quality.

Bean Splits


Bean have been bred, grown, harvested, cooked, canned, inspected and imaged with the goal of creating improved varieties. Here we gathered a small image dataset to evaluate how automatically detected seed coat splits compare with human inspection measures, and to explore the heredity characteristics of this phenotype. More information is available at:

Y. Long, A. Bassett, K. Cichy, A. Thompson, D. Morris, "Bean Split Ratio for Dry Bean Canning Quality and Variety Analysis." To appear in Proc. of Computer Vision Problems in Plant Phenotyping (CVPPP), Jun 2019.

A pre-release of this paper is available on arXiv.

Our dataset will be available here soon!



This research is a collaboration of the 3D Vision Lab, Cichy Lab, and Thompson Lab, and is in part sponsored by the NSF NRT-IMPACTS program at MSU.