Thema4896
Abschlussarbeitstyp: Master
Betreuer: Harald Sack, Etienne Posthumus
Forschungsgruppe: Information Service Engineering
Partner: FIZ Karlsruhe
Archivierungsnummer: 4896
Abschlussarbeitsstatus: Offen
Beginn:
06. Mai 2022
Abgabe: unbekannt
ICONCLASS [1] is the de facto global standard for the subject classification of cultural heritage content. It consists of alphanumeric “notations” which document the subjects in images in a language independent way. These notations have been applied to a large corpus of images. In your thesis, an analysis will be done on the possibilities of linking the notations to specific regions of images [2]. Techniques from computer vision like object detection [3] will be explored, and the option of doing human assisted tagging using serious gaming techniques considered. You will gain experience in developing software for describing and tagging large scale image collections. \n [1] https://iconclass.org/ [2] https://recogito.github.io/annotorious/ [3] https://en.wikipedia.org/wiki/Object_detection Which prerequisites should you have? • Good programming skills in Python • Knowledge of front-end libraries and web programming It also helps if you have an interest or affinity with Art History or Cultural Heritage Contents
Download: Download (pdf)