JEZIK: A Cognitive Translation System Employing a Single, Visible Spectrum Tracking Detector

Davor Bzik, Brigham Young University - Provo


A link between eye movement mechanics and the mental processing associated with text reading has been established in the past. The pausing of an eye gaze on a specific word within a sentence reflects correctness or fluency of a translated text. A cognitive translation system has been built employing a single, inexpensive web camera without the use of infrared illumination. It was shown that the system translates the text, detects rarely occurring and out-of-context words from eye gaze information, and provides solutions in real time while the user is still reading. The solutions are in form of a translation, definition or synonym for the word in question. The only effort required is that of reading.