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.

This research developed and evaluated the multispectral algorithm derived from hyperspectral line-scan imaging using the machine vision system with an electron-multiplying-charge-coupled-device camera and an imaging spectrograph for the detection of defect Red Delicious apples and distinguish them from normal ones. The algorithm utilized the fluorescence intensities at three wavebands, 676 nm, 714 nm and 779 nm, for computation of a simple threshold function for effective detection of defect apples. The algorithm detected more than 95% of defect apples. The effective detection of defect apples showed that a simple multispectral detection algorithm can be appropriate to be implemented on fast-speed apple processing lines to help in risk reduction and food safety assurance for preventing or minimizing the potential foodborne illness.