Download PDFOpen PDF in browser

Improving the Quality of Student Cards Using AI

10 pagesPublished: January 13, 2025

Abstract

Using the advantages of being a relatively small county and the existence of a central e-infrastructure institution for academia and research, Croatia fosters multiple national in- formation systems in the higher education (HE) area. This has created the sound ecosystem that has enabled the creation of first nation-wide European Student Card (ESC), among others. Student cards are frequently used daily, mainly because of the student nourish- ment system which is in place in Croatia but also for other purposes. The new student card is also available in the digital format, in a national digital wallet mobile application. However, one of the main identifying principles remains the same – the visual inspection of the student’s photograph. Therefore, it is important to ensure the quality of the future card photograph which is being submitted by the student. In this article, we present the leverage of AI method to improve the quality of those photographs. The method is based on multiple convolutional neural networks (CNNs).

Keyphrases: ai, cnn, esc, european student card, neural networks

In: Raimund Vogl, Laurence Desnos, Jean-François Desnos, Spiros Bolis, Lazaros Merakos, Gill Ferrell, Effie Tsili and Manos Roumeliotis (editors). Proceedings of EUNIS 2024 annual congress in Athens, vol 105, pages 39-48.

BibTeX entry
@inproceedings{EUNIS2024:Improving_Quality_Student_Cards,
  author    = {Ognjen Orel and Filip Bajić},
  title     = {Improving the Quality of Student Cards Using AI},
  booktitle = {Proceedings of EUNIS 2024 annual congress in Athens},
  editor    = {Raimund Vogl and Laurence Desnos and Jean-François Desnos and Spiros Bolis and Lazaros Merakos and Gill Ferrell and Effie Tsili and Manos Roumeliotis},
  series    = {EPiC Series in Computing},
  volume    = {105},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/XGHc},
  doi       = {10.29007/6lm2},
  pages     = {39-48},
  year      = {2025}}
Download PDFOpen PDF in browser