Implementation of a semantic app on a mobile device

This work has been finished in April 2016.

The aim of this work is to implement a prototype of an android app in domain of food, which al- lows the user to take a photo of the restaurant menu he/she is interested in, which textual content is translated from the original language into the language of the user. This result will be returned embedded in original photo as a display output. For this purpose there are already available the core technologies Optical Character Recognition (OCR) and Machine Translation (MT). Their integration in the mobile sector would be a new developing domain within which there are not so many apps on the market.

The bridge to the semantic technologies will be the second part of the work, coming out to the part while receiving extracted text. The text will be not only translated, but also semantically enriched by the information and pictures, so that a user can find out more about the content text. Another type of information the user gets, is the nutrition description of the food and their category in sense of vegetarian, vegan, etc.