Rahal, Najoua Vögtlin, Lars Ingold, Rolf 2023 In the last few years, many deep neural network architec- tures, especially Fully Convolutional Networks (FCN), have been proposed in the literature to perform semantic segmentation. These architectures contain many parameters and layers to obtain good results. However, for Historical document images, we show in this paper that there is no need to use so many trainable parameters. An architecture with much fewer parameters can perform better while being lighter for train- ing than the most popular variants of FCN. To have a fair and complete comparison, qualitative and quantitative evaluations are carried out on various datasets using standard pixel-level metrics. application/pdf https://folia.unifr.ch/global/documents/334264 https://folia.unifr.ch/documents/334264/files/layoutanalysisofhistoricaldocumentimagesusingalightfullyconvolutionalnetworks.pdf eng info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-031-41734-4_20 info:eu-repo/semantics/altIdentifier/issn/0302-9743 info:eu-repo/semantics/altIdentifier/isbn/9783031417337 info:eu-repo/semantics/openAccess Rights reserved Document Analysis and Recognition - ICDAR 2023, LNCS. - 2023, vol. 14191, p. 325-341 Historical document images Layout analysis Neural network Deep learning info:eu-repo/classification/udc/root_1 Layout Analysis of Historical Document Images Using a Light Fully Convolutional Network http://purl.org/coar/resource_type/c_5794