Přístupnostní navigace
E-application
Search Search Close
Master's Thesis
Author of thesis: Ing. Vít Hromek
Acad. year: 2025/2026
Supervisor: Ing. Ilona Janáková, Ph.D.
Reviewer: Ing. Peter Honec, Ph.D.
This work addresses the design and partial implementation of a prototype device for automated user age verification by combining information extracted from an identity document with age estimation from a facial image. The work is grounded in a survey of methods for document reading (MRZ/OCR), face processing, and deep-learning-based age estimation, with particular emphasis on the relevant legal framework and personal data protection requirements. Based on these findings, a system architecture is proposed that performs local (edge) processing on an embedded platform to minimize the transfer of sensitive data outside the device. The work also implements a basic processing pipeline. The document module processes a predefined MRZ region of interest (ROI), uses an MRZ recognition and parsing library, and computes the user’s age from the extracted date of birth. The face module detects the face using OpenCV Haar cascades, crops and normalizes the facial region, and then runs an SSR-Net age estimation model deployed via TensorFlow Lite. Outputs from both branches are combined in a fusion module that evaluates compliance with an age threshold and basic consistency between document-derived age and face-based age estimation. The resulting prototype validates the integration concept and forms a basis for future extensions such as liveness detection and systematic evaluation.
age verification; identity document; MRZ; OCR; age estimation; face analysis; deep learning; edge computing; Raspberry Pi; decision fusion; personal data protection; GDPR
Date of defence
09.06.2026
Result of the defence
Defended (thesis was successfully defended)
Grading
A
Process of defence
Student obhájil diplomovou práci. Komise neměla žádné námitky k řešené práci. V průběhu odborné rozpravy student odpověděl na dotazy týkající se ochrany osobních údajů a možného budoucího využití práce.
Language of thesis
Czech
Faculty
Fakulta elektrotechniky a komunikačních technologií
Department
Department of Control and Instrumentation
Study programme
Cybernetics, Control and Measurements (MPC-KAM)
Composition of Committee
doc. Ing. Radovan Hájovský, Ph.D. (předseda) doc. Ing. Zdeněk Bradáč, Ph.D. (místopředseda) Ing. Peter Honec, Ph.D. (člen) Ing. Ilona Janáková, Ph.D. (člen) Ing. Stanislav Klusáček, Ph.D. (člen) Ing. Miloslav Richter, Ph.D. (člen)
Supervisor’s reportIng. Ilona Janáková, Ph.D.
Grade proposed by supervisor: A
Reviewer’s reportIng. Peter Honec, Ph.D.
Grade proposed by reviewer: A
Responsibility: Mgr. et Mgr. Hana Odstrčilová