Discriminating drying method of tarhana using computer vision

Abstract

Tarhana is a traditionally fermented wheat flour product of Turkey which has high nutritional value. A rapid and objective evaluation of tarhana quality by assessing the used drying method is important for producers and packaging companies. A computer vision method was developed to discriminate between drying methods of tarhana. Tarhana samples were prepared with three drying methods: sun dried, oven dried and microwave dried. An image acquisition station was constituted under artificial illumination. Different types of machine learning methods and feature selection methods were tested to find an effective system for the discrimination between drying methods of tarhana using visual texture features with different color components. Experimental results showed that the best accuracy rate (99.5%) was achieved with a K-nearest-neighbors classifier through the feature model based on stepwise discriminant analysis.