Naslov
Computer vision application in the quality evaluation of food products

Autori
Lukinac, Jasmina ; Jukić, Marko

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 9th International Specialized Scientific and Practical Conference / - Kijev : National University of Food Technologies (NUFT), 2020, 14-14

ISBN
978-966-612-246-2

Skup
9th International Specialized Scientific and Practical Conference: Resource and Energy Saving Technologies of Production and Packing of Food Products as the Main Fundamentals of Their Competitiveness

Mjesto i datum
Kijev, Ukrajina, 10.10.2020

Vrsta sudjelovanja
Plenarno

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
computer vision system ; image analysis ; food quality ; non-destructive

Sažetak
The number of available technology based on imaging hardware and decision algorithms is growing in order to decrease the manual inspection. For this purpose, computer vison system (CVS) is being used increasingly in the food industry for quality assurance. Computer vision is a technology that allows the automation of visual inspection and measurement tasks using digital cameras and image analysis techniques. It is an automated process that makes use of a computer to classify data extracted from an object in the form of image. CVS technology plays a key role by giving rapid, precise, and consistent results as well as having relatively low cost. CVS may seem simple enough to understand, but below the surface it is a complex and multidisciplinary field, tied up with a variety of technologies, both old and emerging. The hardware for a typical CVS include lighting, the camera and computer with software for image analysis. Both software and hardware parts of the CVS should be customized to the specific needs of a food, including inspection goals and the type of product to analyze. CVS may use a variety of cameras to act as the machine’s “eyes” depending on the imaging requirements and is possible to find existing objects and to obtain properties belonging to objects from an image. Many properties of fresh food are not visible (like dry-matter, internal damage or firmness), spectrometers and hyperspectral cameras can help in identifying these properties non- destructively. However, it is difficult to have a standard inspection method to detect all types of food, which are diverse in size, shape, appearance, and other characteristics. Beyond color, structure and shape are extremely informative features. Therefore, producers of different types of foods need to improve food quality to meet consumer demands. Computer vision deals with simple identification, measuring and counting better than human vision. This paper deals with application of CVS in food quality evaluation. Food quality research requires an improvement of the available methods for foodstuff inspection. CVS has been extensively applied for food quality assessment, including meat and meat products, fruits and vegetables, nuts, cheese as well as grains and bakery products). Automated counting and sorting system based on image analysis can grade fruits, vegetables, nuts, oysters, etc. according to their shape, size and maturity (for fruits and vegetables), increasing the sorting speed by 10 times compared to humans. Automated visual check of a filling level and package labeling is another important application of computer vision in the food industry. Besides that, a visual system can check the freshness of a packed product with the aid of a special ink changing its color with time and at a different speed depending on the temperature.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Prehrambena tehnologija

POVEZANOST RADA