Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shahi, Mojtaba, Rajabi, Roozbeh, Masoumzadeh, Farnaz
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2411.10330
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909391709536256
author Shahi, Mojtaba
Rajabi, Roozbeh
Masoumzadeh, Farnaz
author_facet Shahi, Mojtaba
Rajabi, Roozbeh
Masoumzadeh, Farnaz
contents This article addresses the gap in computational painting analysis focused on Persian miniature painting, a rich cultural and artistic heritage. It introduces a novel approach using Convolutional Neural Networks (CNN) to classify Persian miniatures from five schools: Herat, Tabriz-e Avval, Shiraz-e Avval, Tabriz-e Dovvom, and Qajar. The method achieves an average accuracy of over 91%. A meticulously curated dataset captures the distinct features of each school, with a patch-based CNN approach classifying image segments independently before merging results for enhanced accuracy. This research contributes significantly to digital art analysis, providing detailed insights into the dataset, CNN architecture, training, and validation processes. It highlights the potential for future advancements in automated art analysis, bridging machine learning, art history, and digital humanities, thereby aiding the preservation and understanding of Persian cultural heritage.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10330
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CNN-Based Classification of Persian Miniature Paintings from Five Renowned Schools
Shahi, Mojtaba
Rajabi, Roozbeh
Masoumzadeh, Farnaz
Computer Vision and Pattern Recognition
This article addresses the gap in computational painting analysis focused on Persian miniature painting, a rich cultural and artistic heritage. It introduces a novel approach using Convolutional Neural Networks (CNN) to classify Persian miniatures from five schools: Herat, Tabriz-e Avval, Shiraz-e Avval, Tabriz-e Dovvom, and Qajar. The method achieves an average accuracy of over 91%. A meticulously curated dataset captures the distinct features of each school, with a patch-based CNN approach classifying image segments independently before merging results for enhanced accuracy. This research contributes significantly to digital art analysis, providing detailed insights into the dataset, CNN architecture, training, and validation processes. It highlights the potential for future advancements in automated art analysis, bridging machine learning, art history, and digital humanities, thereby aiding the preservation and understanding of Persian cultural heritage.
title CNN-Based Classification of Persian Miniature Paintings from Five Renowned Schools
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.10330