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.

Color Machine Vision System: An Alternative for Color Measurement

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

Citation:  Pp. 93-100 in Proceedings of the World Congress of Computers in Agriculture and Natural Resources (13-15, March 2002, Iguacu Falls, Brazil)  701P0301.(doi:10.13031/2013.8317)
Authors:   D.A. Luzuriaga, M. O. Balaban
Keywords:   Machine vision, color measurement, RGB, L* a* b*

Color is an important quality attribute, and is used as a predictor of quality, composition, and standards of identity. Most materials do not have uniform surfaces or a single color. Therefore, current measurement by colorimeters or spectrophotometers have difficulties in accurately measuring total color. The objective of this study was to develop a color machine vision system (CMVS) to identify and quantify the color of materials. The CMVS had a light box and a CCD color camera connected to a computer with a frame grabber. Software developed for the Windows 98 environment was used to capture images and obtain RGB color information. This can be converted into L a b, XYZ or Munsell color systems. A color calibration procedure was implemented to correct for changes in light sources, reflections, or camera sensitivity. Results are obtained as histograms or patterns of the samples color spectrum. The average L a b values of the sample can also be calculated. The system was used to quantify the amount of marbling in meat cuts, the degree of browning in fruits and vegetables, the amount of melanosis in shrimp, and to identify apple cultivars.

(Download PDF)    (Export to EndNotes)