A presentation paper at the 15th conference on Sensing for Food Quality and Safety (proceedings here – purchase required) reported on the use of Hyperspectral Imaging (HSI) to screen commercial batches of almonds for adulteration/contamination with bitter almonds. HSI integrates Near Infra Red spectroscopy (which provides an average spectrum for the batch) with spatial information. The authors reported a classification success of 99% in cross-validation and that the pixel-by-pixel validation identified 61 – 85% of adulterated samples. They conclude that HSI is a promising approach for the classification of almonds by bitterness, allowing the identification of each single bitter almond present in the batch.
Photo by CHUTTERSNAP on Unsplash
Comments