izpis_h1_title_alt

Globoki modeli avtorstva umetniških slik
Ilenič, Nejc (Author), Zupan, Blaž (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (23,24 MB)
MD5: 7A17C9C26C514058E50B582CDCEC6373

Abstract
Vse več raziskav se osredotoča na problem avtomatskega prepoznavanja slikarjev iz digitaliziranih umetniških slik. V tem delu se omenjenega izziva lotimo na nadzorovan način, z uporabo konvolucijske nevronske mreže, ki je zaradi visoke izrazne moči sposobna napovedovanja velikega števila avtorjev iz nizkoresolucijskih slik. Predlagano rešitev ovrednotimo na tekmovanju spletnega portala Kaggle, kjer je za pare digitalnih umetnin potrebno napovedati, ali sta delo istega slikarja. V nalogi pokažemo, da značilke, izpeljane iz tem in motivov slik, podobno kot nižjenivojske značilke vsebujejo inherentne lastnosti, ki so primerne za razlikovanje med avtorji.

Language:English
Keywords:strojno učenje, globoki modeli, konvolucijske nevronske mreže, umetniške slike
Work type:Master's thesis/paper (mb22)
Organization:FRI - Faculty of computer and information science
Year:2017
Views:799
Downloads:531
Metadata:XML RDF-CHPDL DC-XML DC-RDF
 
Average score:(0 votes)
Your score:Voting is allowed only to logged in users.
:
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Secondary language

Language:Slovenian
Title:Deep models of painting authorship
Abstract:
An increasing number of studies are investigating how to automatically recognize painters from digital artwork images. We approach this problem in a supervised manner, by training a high-capacity convolutional neural network, capable of predicting a large number of artists from low-resolution scans. We evaluate the proposed solution in a Kaggle competition, in which pairs of paintings need to be classified based on the identity of their authors. The main contribution of our work is the provision of empirical evidence that themes and motifs, similar to low-level features, contain discriminative potential for identifying painters.

Keywords:machine learning, deep models, convolutional neural networks, artwork images

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Comments

Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back