A new imaging method for food inspection

Most importantly, this technology can provide a robust and reliable method of foreign body detection in foodstuffs. Applications include: the detection of fat and bones on chicken; distinguishing between sugar/salt and citric acid; identifying bruising in oranges, apple sorting, coffee bean inspection, turkey and pork differentiation, raisin sorting, pistachio shell identification, pet food inspection (differentiating stones/clay from dog food pellets) and many more. 

The technique is based on the fact that organic materials selectively absorb light at different wavelengths in the infrared region of the spectrum depending on their composition. These distinctive ‘fingerprints’ can be used to uniquely identify them. In hyperspectral imaging it is possible to produce an image where each pixel is colour coded according to the chemical composition of the material it is looking at. It is then possible to use standard machine vision colour sorting solutions. The left hand image shows a traditional colour image of a mixture of pistachio nuts, shells and skin. Any colour differences seen are not sufficient to identify the different components. The right hand image, however, shows the hyperspectral image showing the nuts as red, the shells blue and the skin green. Not only are the component parts clearly distinguished for sorting it is also possible to differentiate those nuts that still have some skin attached.

STEMMER IMAGING has developed a complete, modular hyperspectral imaging system for traditional machine vision users, consisting of all the hardware and software needed and tailored to the particular application.