内容简介:Using the neural-net tool Artbreeder, Photoshop and historical referencesA limited edition printThe main technology behind
54 Machine-learning assisted portraits
Jul 24 ·3min read
Using the neural-net tool Artbreeder, Photoshop and historical references , I have created photoreal portraits of Roman Emperors. For this project, I have transformed, or restored (cracks, noses, ears etc.) 800 images of busts to make the 54 emperors of The Principate (27 BC to 285 AD).
A limited edition print available here .
The Principate — Notes and References
- [Pt I] 27 BC–68 AD: Julio-Claudian dynasty (Augustus; Tiberius; Caligula; Claudius; Nero)
- [Pt II] 68–96: Year of the Four Emperors and Flavian dynasty (Galba; Otho; Vitellius; Vespasian; Titus; Domitian)
- [Pt III] 96–192: Nerva–Antonine dynasty (Nerva; Trajan; Hadrian; Antoninus Pius; Lucius Verus; Marcus Aurelius; Commodus; Pertinax; Didius Julianus; Septimius Severus; Caracalla; Geta; Macrinus; Diadumenian; Elagabalus; Severus Alexander)
- [Pt IV] 235–285: Gordian dynasty and Crisis of the Third Century (Maximinus Thrax; Gordian I; Gordian II; Pupienus; Balbinus; Gordian III; Philip the Arab; Philip II; Decius; Herennius Etruscus; Hostilian; Trebonianus Gallus; Volusianus; Aemilian; Valerian; Gallienus; Saloninus; Claudius Gothicus; Quintillus; Aurelian; Ulpia Severina; Tacitus; Florianus; Probus; Carus; Carinus; Numerian)
The main technology behind Artbreeder is it’s generative adversarial network (GAN). Some call it Artificial Intelligence but it is more accurately described as Machine Learning.
Artistic interpretations are, by their nature, more art than science but I’ve made an effort to cross-reference their appearance (hair, eyes, ethnicity etc.) to historical texts and coinage. I’ve striven to age them according to the year of death — their appearance prior to any major illness.
My goal was not to romanticize emperors or make them seem heroic. In choosing bust / sculptures, my approach was to favor the bust that was made when the emperor was alive. Otherwise, I favored the bust made with the greatest craftsmanship and where the emperor was stereotypically uglier — my pet theory being that artists were likely trying to flatter their subjects.
Some emperors (latter dynasties, short reigns) did not have surviving busts. For this, I researched multiple coin depictions, family tree and birthplaces. Sometimes I created my own composites.
以上就是本文的全部内容,希望本文的内容对大家的学习或者工作能带来一定的帮助,也希望大家多多支持 码农网
本站部分资源来源于网络,本站转载出于传递更多信息之目的,版权归原作者或者来源机构所有,如转载稿涉及版权问题,请联系我们。
机器学习实践指南
麦好 / 机械工业出版社 / 2014-4-1 / 69.00
《机器学习实践指南:案例应用解析》是机器学习及数据分析领域不可多得的一本著作,也是为数不多的既有大量实践应用案例又包含算法理论剖析的著作,作者针对机器学习算法既抽象复杂又涉及多门数学学科的特点,力求理论联系实际,始终以算法应用为主线,由浅入深以全新的角度诠释机器学习。 全书分为准备篇、基础篇、统计分析实战篇和机器学习实战篇。准备篇介绍了机器学习的发展及应用前景以及常用科学计算平台,主要包括统......一起来看看 《机器学习实践指南》 这本书的介绍吧!