Click on “Download PDF” for the PDF version or on the title for the HTML version.
If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.
Smartphone Application for Assessing Peanut Maturity
Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.orgCitation: Transactions of the ASABE. 63(2): 339-344. (doi: 10.13031/trans.13579) @2020
Authors: Zhuo Zhao, Brian L. Boland, Farid Ghareh Mohammadi, Walter S. Monfort, Kyle Johnsen, Zion T. H. Tse, Donald J. Leo
Keywords: Mesocarp color, Peanut maturity grading, Peanut sorting board, Smartphone application.
Optimal harvest date is important to improve the yield and quality of peanut.
Peanut mesocarp color is one of the most popular methods for determining the optimal harvest date.
This article presents a smartphone-based system for determining optimal harvest date based on peanut mesocarp color.
Abstract. Harvesting at the right time is crucial to ensuring the best quality peanuts and maximizing yield. This article presents an offline system to assist farmers in evaluating peanut maturity. The system uses an automated method to determine peanut pod maturity, and it is portable, so it can be used in the field. Peanut maturity evaluation in the proposed system is based on the color of the mesocarp, which is the middle layer of the peanut shell. The mesocarp changes color over time from white to yellow, then dark brown, and finally black as the peanut reaches maturity. In the developed system, peanut pods are placed on a specially designed peanut sorting board, and the mesocarp color of each peanut pod is quantified by measuring the red, green, and blue (RGB) values with a smartphone camera. A nearest-neighbor classification algorithm is then used to sort each peanut into one of 25 colors on a color bar, which represents the different peanut maturity levels. To estimate the overall crop maturity, the ratio of the number of peanuts in the combined brown-black class to the total sample size must be determined. Using the developed system, this ratio was identified with 88.99% accuracy. In addition, the experimental results show that the inter-rater reliability of the developed system is comparable with manual methods involving human graders. Therefore, the system presented in this article shows great promise as a tool for helping to evaluate the maturity of peanut crops.(Download PDF) (Export to EndNotes)