Matches in SemOpenAlex for { <https://semopenalex.org/work/W2767985513> ?p ?o ?g. }
- W2767985513 abstract "Autoimmune diseases are the third cause of mortality in the world. The identification of anti-nuclear antibody (ANA) via Immunofluorescence (IIF) test in human epithelial type-2 cells (HEp-2) is a conventional method to support the diagnosis of such diseases. In the present work, three popular Convolutional Neural Networks (CNNs) are evaluated for this task: LeNet-5, AlexNet, and GoogLeNet. We also assess the impact of six different pre-processing strategies on the performance of these CNNs. Additionally, data augmentation based on the rotation of the training set images after the pre-processing strategies was evaluated. Our work is the first to consider AlexNet and GoogLeNet models for the proposed analysis and classification of HEp-2 cells images, besides the LeNet-5. Experimental results allow to conclude that neither pre-processing strategies were essential to improve accuracy values of the CNNs. However, when data augmentation is considered, contrast enhancement followed by data centralization is significant in order to achieve good results. Additionally, our results were compared with results from other state-of-art papers. Our best results were achieved by GoogLeNet architecture trained with images with no pre-processing and no data augmentation, resulting in 98.17% of accuracy, which outperforms the results presented in other works in literature." @default.
- W2767985513 created "2017-11-17" @default.
- W2767985513 creator A5067260516 @default.
- W2767985513 creator A5081258813 @default.
- W2767985513 creator A5090987423 @default.
- W2767985513 date "2017-10-01" @default.
- W2767985513 modified "2023-09-30" @default.
- W2767985513 title "Exploiting Convolutional Neural Networks and Preprocessing Techniques for HEp-2 Cell Classification in Immunofluorescence Images" @default.
- W2767985513 cites W1534935660 @default.
- W2767985513 cites W1791065060 @default.
- W2767985513 cites W1806891645 @default.
- W2767985513 cites W1849277567 @default.
- W2767985513 cites W1965727970 @default.
- W2767985513 cites W2001414865 @default.
- W2767985513 cites W2004801324 @default.
- W2767985513 cites W2006536906 @default.
- W2767985513 cites W2007442867 @default.
- W2767985513 cites W2007815737 @default.
- W2767985513 cites W2043582592 @default.
- W2767985513 cites W2045206174 @default.
- W2767985513 cites W2054108035 @default.
- W2767985513 cites W2056052642 @default.
- W2767985513 cites W2059272842 @default.
- W2767985513 cites W2062073991 @default.
- W2767985513 cites W2062118960 @default.
- W2767985513 cites W2085770918 @default.
- W2767985513 cites W2095705004 @default.
- W2767985513 cites W2096871134 @default.
- W2767985513 cites W2097117768 @default.
- W2767985513 cites W2108598243 @default.
- W2767985513 cites W2112796928 @default.
- W2767985513 cites W2122092925 @default.
- W2767985513 cites W2141619730 @default.
- W2767985513 cites W2146862352 @default.
- W2767985513 cites W2155893237 @default.
- W2767985513 cites W2163605009 @default.
- W2767985513 cites W2176950688 @default.
- W2767985513 cites W2253429366 @default.
- W2767985513 cites W2253913666 @default.
- W2767985513 cites W2312404985 @default.
- W2767985513 cites W2509789594 @default.
- W2767985513 cites W2563353037 @default.
- W2767985513 cites W2914484425 @default.
- W2767985513 cites W2919115771 @default.
- W2767985513 cites W2955331105 @default.
- W2767985513 cites W2962835968 @default.
- W2767985513 cites W36489998 @default.
- W2767985513 cites W2507697486 @default.
- W2767985513 doi "https://doi.org/10.1109/sibgrapi.2017.29" @default.
- W2767985513 hasPublicationYear "2017" @default.
- W2767985513 type Work @default.
- W2767985513 sameAs 2767985513 @default.
- W2767985513 citedByCount "6" @default.
- W2767985513 countsByYear W27679855132017 @default.
- W2767985513 countsByYear W27679855132018 @default.
- W2767985513 countsByYear W27679855132019 @default.
- W2767985513 countsByYear W27679855132021 @default.
- W2767985513 crossrefType "proceedings-article" @default.
- W2767985513 hasAuthorship W2767985513A5067260516 @default.
- W2767985513 hasAuthorship W2767985513A5081258813 @default.
- W2767985513 hasAuthorship W2767985513A5090987423 @default.
- W2767985513 hasConcept C108583219 @default.
- W2767985513 hasConcept C153180895 @default.
- W2767985513 hasConcept C154945302 @default.
- W2767985513 hasConcept C169903167 @default.
- W2767985513 hasConcept C34736171 @default.
- W2767985513 hasConcept C41008148 @default.
- W2767985513 hasConcept C52622490 @default.
- W2767985513 hasConcept C58489278 @default.
- W2767985513 hasConcept C81363708 @default.
- W2767985513 hasConceptScore W2767985513C108583219 @default.
- W2767985513 hasConceptScore W2767985513C153180895 @default.
- W2767985513 hasConceptScore W2767985513C154945302 @default.
- W2767985513 hasConceptScore W2767985513C169903167 @default.
- W2767985513 hasConceptScore W2767985513C34736171 @default.
- W2767985513 hasConceptScore W2767985513C41008148 @default.
- W2767985513 hasConceptScore W2767985513C52622490 @default.
- W2767985513 hasConceptScore W2767985513C58489278 @default.
- W2767985513 hasConceptScore W2767985513C81363708 @default.
- W2767985513 hasLocation W27679855131 @default.
- W2767985513 hasOpenAccess W2767985513 @default.
- W2767985513 hasPrimaryLocation W27679855131 @default.
- W2767985513 hasRelatedWork W2059272842 @default.
- W2767985513 hasRelatedWork W2097117768 @default.
- W2767985513 hasRelatedWork W2606416966 @default.
- W2767985513 hasRelatedWork W2760244101 @default.
- W2767985513 hasRelatedWork W2785868282 @default.
- W2767985513 hasRelatedWork W2791460829 @default.
- W2767985513 hasRelatedWork W2794335896 @default.
- W2767985513 hasRelatedWork W2810323699 @default.
- W2767985513 hasRelatedWork W2810901376 @default.
- W2767985513 hasRelatedWork W2899142219 @default.
- W2767985513 hasRelatedWork W2945830552 @default.
- W2767985513 hasRelatedWork W2948594902 @default.
- W2767985513 hasRelatedWork W2966436072 @default.
- W2767985513 hasRelatedWork W2984155152 @default.
- W2767985513 hasRelatedWork W2989573210 @default.
- W2767985513 hasRelatedWork W3014041368 @default.
- W2767985513 hasRelatedWork W3034049613 @default.
- W2767985513 hasRelatedWork W3157615104 @default.