Research Information System
QUALITY ASSURANCE AND SAFETY OF CROPS & FOODS, vol.2, no.4, pp.203-207, 2010 (SCI-Expanded)
Background and Aim High concentrations of acrylamide found in common fried and baked foods attained considerable public concern since it has been classified as a probable human carcinogen. Many analytical methods have been published for the determination of acrylamide in foods. Although these methods perform well for quality control purposes in a food analysis laboratory, they are laborious, costly, and cannot be adopted for process control purposes by the food industry. This study describes a computer vision-based image analysis algorithm using color segmentation for the prediction of acrylamide level in thermally processed foods. Materials and Methods Laboratory made experimental potato crisps and cookies were prepared by frying and baking, respectively. The digital images of potato crisps and cookies were used to extract a meaningful browning parameter. Results and Conclusion The digital images were analyzed using a semiautomatic segmentation algorithm to calculate the browning ratio of potato crisps and cookies. The calculated browning ration were successfully correlated with acrylamide level of cookies and potato crisps. So, it was possible to predict the levels of acrylamide in test samples by means of their browning ratio values. The image analysis technique described here can be used as an online process control tool for frying and baking industry.