000904117 001__ 904117
000904117 005__ 20240712084513.0
000904117 0247_ $$2doi$$a10.1109/JPHOTOV.2020.3041240
000904117 0247_ $$2ISSN$$a2156-3381
000904117 0247_ $$2ISSN$$a2156-3403
000904117 0247_ $$2Handle$$a2128/30280
000904117 0247_ $$2WOS$$aWOS:000621413300027
000904117 037__ $$aFZJ-2021-05687
000904117 082__ $$a530
000904117 1001_ $$0P:(DE-Juel1)177942$$aSovetkin, Evgenii$$b0
000904117 245__ $$aEncoder–Decoder Semantic Segmentation Models for Electroluminescence Images of Thin-Film Photovoltaic Modules
000904117 260__ $$aNew York, NY$$bIEEE$$c2021
000904117 3367_ $$2DRIVER$$aarticle
000904117 3367_ $$2DataCite$$aOutput Types/Journal article
000904117 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1642420812_31326
000904117 3367_ $$2BibTeX$$aARTICLE
000904117 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000904117 3367_ $$00$$2EndNote$$aJournal Article
000904117 520__ $$aWe consider a series of image segmentation methods based on the deep neural networks in order to perform semantic segmentation of electroluminescence (EL) images of thin-film modules. We utilize the encoder-decoder deep neural network architecture. The framework is general such that it can easily be extended to other types of images (e.g., thermography) or solar cell technologies (e.g., crystalline silicon modules). The networks are trained and tested on a sample of images from a database with 6000 EL images of copper indium gallium diselenide thin film modules. We selected two types of features to extract, shunts and so called “droplets.” The latter feature is often observed in the set of images. Several models are tested using various combinations of encoder-decoder layers, and a procedure is proposed to select the best model. We show exemplary results with the best selected model. Furthermore, we applied the best model to the full set of 6000 images and demonstrate that the automated segmentation of EL images can reveal many subtle features, which cannot be inferred from studying a small sample of images. We believe these features can contribute to process optimization and quality control.
000904117 536__ $$0G:(DE-HGF)POF4-1215$$a1215 - Simulations, Theory, Optics, and Analytics (STOA) (POF4-121)$$cPOF4-121$$fPOF IV$$x0
000904117 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000904117 7001_ $$0P:(DE-HGF)0$$aAchterberg, Elbert Jan$$b1
000904117 7001_ $$0P:(DE-HGF)0$$aWeber, Thomas$$b2
000904117 7001_ $$0P:(DE-Juel1)130284$$aPieters, Bart E.$$b3$$eCorresponding author
000904117 773__ $$0PERI:(DE-600)2585714-9$$a10.1109/JPHOTOV.2020.3041240$$gVol. 11, no. 2, p. 444 - 452$$n2$$p444 - 452$$tIEEE journal of photovoltaics$$v11$$x2156-3381$$y2021
000904117 8564_ $$uhttps://juser.fz-juelich.de/record/904117/files/2010.07556.pdf$$yOpenAccess
000904117 8564_ $$uhttps://juser.fz-juelich.de/record/904117/files/EncoderDecoder_Semantic_Segmentation_Models_for_Electroluminescence_Images_of_Thin-Film_Photovoltaic_Modules.pdf$$yRestricted
000904117 909CO $$ooai:juser.fz-juelich.de:904117$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000904117 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177942$$aForschungszentrum Jülich$$b0$$kFZJ
000904117 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)130284$$aForschungszentrum Jülich$$b3$$kFZJ
000904117 9131_ $$0G:(DE-HGF)POF4-121$$1G:(DE-HGF)POF4-120$$2G:(DE-HGF)POF4-100$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-1215$$aDE-HGF$$bForschungsbereich Energie$$lMaterialien und Technologien für die Energiewende (MTET)$$vPhotovoltaik und Windenergie$$x0
000904117 9141_ $$y2021
000904117 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2021-01-26
000904117 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology$$d2021-01-26
000904117 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bIEEE J PHOTOVOLT : 2019$$d2021-01-26
000904117 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2021-01-26
000904117 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2021-01-26
000904117 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2021-01-26
000904117 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000904117 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2021-01-26
000904117 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2021-01-26
000904117 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2021-01-26
000904117 920__ $$lyes
000904117 9201_ $$0I:(DE-Juel1)IEK-5-20101013$$kIEK-5$$lPhotovoltaik$$x0
000904117 9801_ $$aFullTexts
000904117 980__ $$ajournal
000904117 980__ $$aVDB
000904117 980__ $$aUNRESTRICTED
000904117 980__ $$aI:(DE-Juel1)IEK-5-20101013
000904117 981__ $$aI:(DE-Juel1)IMD-3-20101013