I-Corps: Smartphone-based peanut maturity grading and analytic system

点击翻译按钮获取中文摘要

The broader impact/commercial potential of this I-Corps project will be the improvement of crop yield and quality by providing accurate and consistent color-based peanut classification. Many crops are based on color classification to determine the harvest day and quality. Also, optimizing harvest dates is a key to maximizing peanut quality and production. A loss of the total yield can be caused by underestimating or overestimating the harvest dates. In addition, overestimation can cause a low selling price and suboptimal peanut quality due to immaturity, while underestimation may cause over-mature crops to be left in the soil due to the weak stems. Currently, the color classification procedures in peanuts are human-vision based. Comparing to them, this technology will provide a standardized, accurate and consistent peanut grading results. Also, the accumulated data will provide updated insights to financial institutes, food industries, growers on peanut pricing, yield and quality. This I-Corps program will provide opportunities for the team to explore commercialization of the technology.This I-Corps project is the first peanut maturity prediction and analytic system designed to streamline and simplify the current procedure. Existing method for maturity prediction is based on human vision, which can lead to variability in results due to the subjective nature of the test, and 30+ minutes to finish one set of 200+ peanut samples. In this proposal, a standardized peanut maturity prediction and analytic system based on color classification has been developed. The system includes a light-controlled photo booth, a peanut sorting board and a smartphone to grade and analyze up to 400 peanuts each time. Automation will allow the grading process to be completed in under 3 minutes and generate a report for the user. This will help save 500-800 hours of labor cost per peanut grader in each peanut season. Furthermore, a peanut information system will be developed to collect peanut information through the grading procedure. This information can be used for providing pricing and growth prediction information in the peanut market. Several prototypes have been developed to prove the concept. Tests have been performed with peanut samples to prove the concept of the proposed technology.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.