Machine Learning and Computer Vision in the Humanities

DSpace/Manakin Repository

Show simple item record

dc.contributor.advisor Warglien, Massimo it_IT
dc.contributor.author Dassiè, Federico <1997> it_IT
dc.date.accessioned 2022-10-26 it_IT
dc.date.accessioned 2023-02-22T11:18:38Z
dc.date.available 2023-02-22T11:18:38Z
dc.date.issued 2022-11-03 it_IT
dc.identifier.uri http://hdl.handle.net/10579/22604
dc.description.abstract Saranno discussi i modi in cui il mondo del Machine Learning e della Computer Vision si stanno presentando al giorno d'oggi e di come, nel nostro caso, siano stati di fondamentale aiuto per migliorare l'esperienza lavorativa e soprattutto garantire una migliore efficienza tecnica. Saranno presentati numerosi esempi personali e dimostrazioni, basati su commissioni fatte e aspirazioni future. Nella fattispecie, la tesi si concentra sul lavoro svolto presso la Fondazione Giorgio Cini, che prevede una catena di passaggi automatici che parte dall'immagine grezza e arriva alla sua completa analisi finale, passando per una fase di post-produzione e la creazione e l'utilizzo di un modello classificatore. it_IT
dc.language.iso en it_IT
dc.publisher Università Ca' Foscari Venezia it_IT
dc.rights © Federico Dassiè, 2022 it_IT
dc.title Machine Learning and Computer Vision in the Humanities it_IT
dc.title.alternative Machine Learning and Computer Vision in the Humanities it_IT
dc.type Master's Degree Thesis it_IT
dc.degree.name Digital and public humanities it_IT
dc.degree.level Laurea magistrale it_IT
dc.degree.grantor Dipartimento di Studi Umanistici it_IT
dc.description.academicyear 2021-2022_appello_171022 it_IT
dc.rights.accessrights openAccess it_IT
dc.thesis.matricno 861867 it_IT
dc.subject.miur INF/01 INFORMATICA it_IT
dc.description.note We will discuss the ways in which the world of Machine Learning and Computer Vision are presenting themselves nowadays and how, in our case, they have been of fundamental help in improving the work experience and above all guaranteeing better technical efficiency. Preserving heritage, whether it will be a physical or digital aspect, is and always will be a difficult goal to reach. The main problem is given by the vastness of materials of different types, which make treatment difficult and lengthen the times. Since it is impossible or at least exhausting to carry out all the processing work by hand, image by image, it is necessary to be able to automate the process. The thesis focuses on the work carried out at the Giorgio Cini Foundation, which includes a chain of automatic steps that starts from the raw image and arrives at its complete final analysis, passing through a post-production phase and the creation and use of an Object Detection model. The final result are the same starting images, now corrected according to different transformations and parameters, with a series of statistical information about their contents, both ready to be published for a broader public. it_IT
dc.degree.discipline it_IT
dc.contributor.co-advisor it_IT
dc.date.embargoend it_IT
dc.provenance.upload Federico Dassiè (861867@stud.unive.it), 2022-10-26 it_IT
dc.provenance.plagiarycheck Massimo Warglien (warglien@unive.it), 2022-10-17 it_IT


Files in this item

This item appears in the following Collection(s)

Show simple item record