Eureka! Institutional Repository

The purpose of this thesis is to investigate whether digital food images is a reliable method of nutritional evaluation in combination with other methods, as well as whether it is possible to accurately identify the food depicted in the images.For this reason, 2861 digital images of afternoon snacks of children aged 9 to 18 from 23 schools in Thessaloniki belonging to the municipalities of Ampelokipi-Menemeni and Pylaia-Chortiati were studied and analyzed. For the analysis of digital images, the VIA Image Annotator software was used, which can accurately determine the outline of each food and add metadata to each photo. To achieve this, a set of data for this research was created and added to the software. The digital images were analyzed and evaluated one after the other, highlighting the corresponding information in each photo. Specifically, this thesis investigated (1) the types of snacks (at the level of food category), (2) the consumption of highly processed foods (ultra-processed) and (3) whether the children’s snacks options follow the recommendations of Ministry Health and the general rules of healthy eating. It was also investigated whether there were differences in these three categories of data based on possible socio–economic differences arising from the municipality to which each school belongs. Taking into consideration the results of the statistical analysis and the graphs depicting them, it was found that the nutritional evaluation through digital images is reliable but also pleasant compared to other methods of nutritional evaluation such as 24-hour recall or the recording of weighed foods. In addition, it was found that the largest percentage of children (50%) in both municipalities consumed highly processed foods as well as foods that are not recommended as snacks but there were no significant differences between the two municipalities.