engleski

Quality inspection of cookies using computer vision

Product appearance plays a vital role making a purchase decision, with colour, size and shape significantly influencing impulse purchases of bakery products. Food material shape is often closely related to its quality. Broken or deformed product may taste the same as an acceptable one, but customers are reluctant to buy seemingly damaged goods. Due to the demands of high quality, automated food shape inspection has become an important need for the food industry. Computer vision provides one alternative for an automated, non-destructive and cost-effective technique to accomplish these requirements. Features such as the internal and external appearance contribute to the overall impression of the products quality. Consequently such characteristics have been evaluated by computer vision. The goal of this paper is to summarize and evaluate shape descriptors which can be used as indicators of final product, and also as additional parameter for decision an ending of baking process. According to results of size (width and height) and shape deformation of cookies during baking process, computer vision can be applied to inspect shape of final product and in combination with other process parameters better define the end of baking process. We believe that the proposed framework opens up new possibilities in the field of non- destructive, visual inspection of cookies (i.e. inspection texture and colour).

computer vision ; food quality ; shape descriptors

nije evidentirano