Abstract
AbstractQuality classification of wine natural cork stoppers is related to presence of discontinuities in the cork tissue. Automated image analysis of stoppers based on black and white cameras is used industrially for commercial classification but recently color has been introduced in image processing. This paper compares the performance of three image vision systems regarding classification accuracy of cork stoppers of good, medium and inferior quality: black and white, three‐band RGB color and manual detection by digitalization in color image. A canonical discriminant analysis approach was used to compare the discriminating power between cork stopper quality in each vision system. Good discriminant results were obtained with the area of pores expressed either in total or as ratio, mean or maximum value. The use of color slightly enlarges the range of cork inspection systems and automated systems have a similar accuracy of classification to visual inspection. Copyright © 2007 Society of Chemical Industry
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have