%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 11:54:44 AM

@ARTICLE{Villamizar_PRL_2020,
         author = {Villamizar, Michael and Can{\'{e}}vet, Olivier and Odobez, Jean-Marc},
       projects = {Idiap},
          title = {Multi-scale sequential network for semantic text segmentation and localization},
        journal = {Pattern Recognition Letters},
         volume = {129},
           year = {2020},
          pages = {63-69},
           issn = {0167-8655},
            url = {http://www.sciencedirect.com/science/article/pii/S0167865519303150},
            doi = {https://doi.org/10.1016/j.patrec.2019.11.001},
       abstract = {We present a novel method for semantic text document analysis which in addition to localizing text it labels the text in user-defined semantic categories. More precisely, it consists of a fully-convolutional and sequential network that we apply to the particular case of slide analysis to detect title, bullets and standard text. Our contributions are twofold: (1) A multi-scale network consisting of a series of stages that sequentially refine the prediction of text and semantic labels (text, title, bullet); (2) A synthetic database of slide images with text and semantic annotation that is used to train the network with abundant data and wide variability in text appearance, slide layouts, and noise such as compression artifacts. We evaluate our method on a collection of real slide images collected from multiple conferences, and show that it is able to localize text with an accuracy of 95\%, and to classify titles and bullets with accuracies of 94\% and 85\% respectively. In addition, we show that our method is competitive on scene and born-digital image datasets, such as ICDAR 2011, where it achieves an accuracy of 91.1\%.},
            pdf = {https://publications.idiap.ch/attachments/papers/2020/Villamizar_PRL_2020.pdf}
}