Hyperspectral imaging system detects defects on apples
A researcher at the University of Maryland (College Park, MD) has shown that a hyperspectral image processing system can identify accurately 95 percent of the defects on the surface of Red Delicious apples.
A researcher at the University of Maryland (College Park, MD, USA) has shown that a hyperspectral image processing system can identify accurately 95 percent of the defects on the surface of Red Delicious apples.
Hyperspectral imaging is a nondestructive detection technology that integrates conventional imaging and spectroscopy to enable both spatial and spectral information to be acquired from objects such as apples for food safety and quality analysis.
Researcher Tao Tao’s system comprised a line-scan imager that was integrated with a commercial apple sorting machine from FMC (Philadelphia, PA, USA).
The hyperspectral system comprised an Andor (Belfast, Northern Ireland) iXon Du 860 electron-multiplying charge coupled-device (EMCCD) and an ImSpector V10E imaging spectrograph from Spectral Imaging (Oulu, Finland).
The hyperspectral data only captured part of the apple surface that faced the camera. But the researcher says that in the future, the apple sorting machine could rotate the apple enabling the entire 360 degree surface to be examined.
More information on the system can be found in Tao’s Master of Science thesis, which details the selection of the spectral bands and the classification method used to identify the defective apples.
Entitled “Multispectral Method for Apple Defect Detection using Hyperspectral Imaging System”, it can be found here.
-- by Dave Wilson, Senior Editor, Vision Systems Design