Study on interactive face recognition

Gerber, Michael and Ruch, Victor (2017) Study on interactive face recognition. Student Research Project thesis, HSR Hochschule für Technik Rapperswil.

HS 2017 2018-SA-EP-Gerber-Ruch-Studie über interaktive Gesichtserkennung.pdf - Supplemental Material

Download (2MB) | Preview


In recent years, there have been significant advances in the field of face recognition. Many of them are based on deep learning. In our thesis, we investigated the state of the art face recognition technology and its possible applications. The main goal of our work is to build a prototype for the exhibition “Informatik zum Anfassen”. At the beginning, we evaluated different classification technologies (OpenCV, Microsoft Cognitive Services Face API, TensorFlow) and their capabilities. On the results we gathered, we built an early prototype for classification from phones. We changed direction and developed the second prototype that is capable of fully autonomous tracking. Our prototype demonstrates with a full-stack example how embeddings can be used to train an unsupervised online clustering algorithm to track previously unknown people over different locations. To accomplish this, we developed a client-server architecture comprising multiple services to achieve high performance and scalability. We are confident that we have achieved the goal of our thesis with our prototype. It shows the capabilities of modern face recognition technology by applying them effectively to a real world setting. In our opinion it would be a worthwhile addition to the exhibition.

Item Type: Thesis (Student Research Project)
Subjects: Area of Application > Multimedia > Video
Technologies > Programming Languages > C++
Technologies > Programming Languages > Python
Technologies > Databases > MySQL
Divisions: Bachelor of Science FHO in Informatik > Student Research Project
Gerber, MichaelUNSPECIFIED
Thesis advisorBläser, LucUNSPECIFIED
Depositing User: HSR Deposit User
Date Deposited: 10 Apr 2018 09:16
Last Modified: 10 Apr 2018 09:16

Actions (login required)

View Item View Item