TUdatalib : Classification of gravure printed patterns using convolutional neural networks (Python code)

Zur Kurzanzeige

dc.contributor.author	Rothmann-Brumm, Pauline
dc.date.accessioned	2023-05-16T11:26:33Z
dc.date.accessioned	2023-06-13T13:58:31Z
dc.date.available	2023-05-16T11:26:33Z
dc.date.available	2023-06-13T13:58:31Z
dc.date.issued	2023
dc.identifier.uri	https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/3838
dc.identifier.uri	https://doi.org/10.48328/tudatalib-1147
dc.description	This dataset contains Python code ('code_DeepLearn_ImgClass.zip') for automated classification of gravure printed patterns from the <a href="https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/3841">HYPA-p</a> dataset.<br/> <br/> The developed algorithm performs supervised deep learning of convolutional neural networks (CNNs) on labeled data ('CNN_dataset.zip'), i.e. selected, labeled 'S-subfields' from the HYPA-p dataset. 'CNN_dataset.zip' is a subset from the images in the folder 'labeled_data.zip', which can be created with the provided Python code. PyTorch is used as a deep learning framework. The Python code yields trained CNNs, which can be used for automated classification of unlabeled data from the HYPA-p dataset. <br/> <br/> Well-known, pre-trained network architectures like Densenet-161 or MobileNetV2 are used as a starting point for training. Several trained CNNs are included in this submission, see 'trained_CNN_models.zip'. <br/> <br/> Further information can be found in the dissertation of Pauline Rothmann-Brumm (2023) and in the provided README-file.	de_DE
dc.language.iso	en	de_DE
dc.relation	IsSupplementTo;URL;https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/3841
dc.rights	Creative Commons Attribution-NonCommercial 4.0
dc.rights.uri	https://creativecommons.org/licenses/by-nc/4.0/
dc.subject	Python code	de_DE
dc.subject	pattern classification	de_DE
dc.subject	hydrodynamic pattern formation	de_DE
dc.subject	deep learning	de_DE
dc.subject	convolutional neural networks	de_DE
dc.subject	gravure printing	de_DE
dc.subject.classification	4.21-03 Mechanische Verfahrenstechnik	de_DE
dc.subject.classification	4.22-03 Strömungsmechanik	de_DE
dc.subject.classification	4.31-03 Beschichtungs- und Oberflächentechnik	de_DE
dc.subject.ddc	660
dc.subject.ddc	620
dc.title	Classification of gravure printed patterns using convolutional neural networks (Python code)	de_DE
dc.type	Text	de_DE
dc.type	Software	de_DE
dc.type	Image	de_DE
dc.type	Model	de_DE
tud.project	DFG \| SFB1194 \| TP C01 Dörsam	de_DE
tud.unit	TUDa
tud.history.classification	Version=2020-2024;403-03 Mechanische Verfahrenstechnik
tud.history.classification	Version=2020-2024;404-03 Strömungsmechanik
tud.history.classification	Version=2020-2024;405-03 Beschichtungs- und Oberflächentechnik