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.

Durum Wheat Quality Evaluation Software

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  Pp. 49-55 in Proceedings of the World Congress of Computers in Agriculture and Natural Resources (13-15, March 2002, Iguacu Falls, Brazil)  701P0301.(doi:10.13031/2013.8311)
Authors:   L. Bacci, B. Rapi, Colucci and P. Novaro
Keywords:   Computer vision, software development, durum wheat, seed quality

Durum wheat kernel quality is an important factor for food industry affecting the phases of marketing and processing. Nevertheless, at present, there are not automatic systems that allow an objective seed quality determination and the evaluation is usually carried out by experts who visually examine some samples collected from the whole stock. Nowadays there are many examples of machine vision application and image processing in food industry. The transfer of these techniques, aimed to the selection of examined material, from a sector to another one requires deep studies, long time and important financial engagement. Nevertheless the machine vision component applied to the evaluation of products can introduce, at low cost, significant improvements, mainly in the price determination phase: increasing sample number, analysis repeatability, objectivity of the evaluation, etc. This paper describes the procedures and operative solutions that have been set up to apply computer vision techniques to detect and quantify durum wheat caryopsis alterations. The developed system collects images by common digital camera or other image acquisition sources, transfers images to a PC and uses a dedicated software (called W.A.V.E.) for the sample evaluation. The evaluation is based on the comparison between the reference characteristics of unaltered seeds and the characteristics of the examined sample, according to different criteria. The output is the percentage of damaged seeds for each alteration typology. The software enables the user to operate according to different levels of automation: a) low (the user can modify and control all steps of the analysis, included the criteria to be applied for the evaluation); b) medium (the user can modify only some parts of analysis procedure); c) high (the software runs automatically using the default values for image acquisition and evaluation of alterations).

(Download PDF)    (Export to EndNotes)