Institutional Repository of Vilnius University
Veidų panašumo analizės sistema naudojanti tensorflow. js /
Abstract
dc:descriptionThis bachelor thesis presents the development of a facial similarity analysis system operating within a web browser and integrating TensorFlow.js artificial intelligence models. The thesis explores facial recognition technologies, their applications, and associated privacy and ethical challenges, especially regarding biometric data protection. The developed system aims to enable users to analyze the online usage of their images and identify potential privacy threats. It incorporates facial attribute analysis, vectorization, and API integrations to detect similar images published online. The study also evaluates the employed models, their accuracy, and their suitability for a browser environment. The system emphasizes data security and privacy by processing data locally within the user's browser. The research findings suggest that the system can effectively enhance users' understanding and control over their personal data in real-world applications.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Zembleckis, Gabrielius,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD229555034&prefLang=en_US