Abstract

The global consumption of potatoes as food is shifting from fresh potatoes to added-value, processed food products. Potatoes are processed into a great variety of products, including cooked potatoes, par-fried potato strips, french fries, potato chips, potato starch, potato granules, potato flakes, and dehydrated diced potatoes, among others. Potato chips are very thin pieces of sliced raw potatoes that are fried to a final oil and moisture content of ∼35% and 1.8%, respectively. In the potato chip industry, each batch of potato tubers must be tested for quality before processing, and the visual aspect is, of course, of great importance. The color of potato chips is the first quality parameter evaluated by consumers and is critical in the acceptance of the product, even before it enters the mouth. On the other hand, acrylamide has been reported as a critical compound for human health (carcinogenic in rats) that is formed in potatoes during frying and that is highly related to the color of the potato chips. Traditionally the potato chip color has been measured instrumentally with special devices called colorimeters. In some European factories, some computer vision systems have been testing the online evaluation of potato chips, allowing chips to be sorted according to defects like black spots or blisters. Some researchers have been also working on a promising device that should be able both to classify chips according to color and to predict acrylamide levels using neural networks. Finally, some authors have used near infrared spectroscopy (NIR) to investigate the possibilities of using online NIR monitoring of acrylamide, moisture, and oil content in potato chips. The objective of this chapter is to show the application of computer vision techniques to automatically study some quality attributes of potato chips.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call