In the last decade, advancements in artificial intelligence have opened new possibilities for bio-metric authentication of individuals, thereby creating a need for the application of these solutions on mobile devices. In this thesis, we focus on the issue of identifying an individual based on the features of the ear using a mobile device. To address this challenge, we have developed an application based on two main segments: the development of models for detection (the YOLO algorithm) and ear recognition (MobileNetV3) through machine learning, and the implementation of these developed models in the Android studio development tool. Results demonstrate that, with the aid of current technology, it's possible to reliably and successfully recognize ears on mobile devices, opening new paths for further research in this area.
|
