Entity: Universitat Rovira i Virgili (URV)
Confidenciality: Si
Education area(s): Enginyeria de la Seguretat Informàtica i Intel·ligència Artificial
APS: No
Title in different languages: Recognising people by means of clothing or other non-invasive factors
Abstract: This thesis titled explores the development of a non-invasive person recognition system. This system leverages attributes such as clothing and height to enhance ski access control mechanisms, specifically for SKIDATA, the project's sponsor. The thesis covers the theoretical foundation of neural networks, particularly Siamese networks, and details the creation and processing of datasets to train the AI model. It also covers challenges of the process. The approach aims to improve the efficiency and accuracy of recognizing individuals at ski resorts, addressing the legal challenges posed by traditional biometric methods.
Subject: Intel·ligència artificial
Academic year: 2023-2024
Language: en
Work's public defense date: 2024-09-12
Subject areas: Computer engineering
Student: Koeckerbauer, Daniel-Markus
Department: Enginyeria Informàtica i Matemàtiques
Creation date in repository: 2025-10-23
Keywords: AI, person recognition, access control
Title in original language: Recognising people by means of clothing or other non-invasive factors
Access Rights: info:eu-repo/semantics/openAccess
Project director: Serratosa Casanelles, Francesc d'assís
Repositori URV