@InProceedings{OliveiraMeSoJúPeGo:2016:DaAuMe,
               author = "Oliveira, {\'{\I}}talo de Pontes and Medeiros, Jo{\~a}o Lucas 
                         Peixoto and Sousa, Vin{\'{\i}}cius Fernandes de and J{\'u}nior, 
                         Adalberto Gomes Teixeira and Pereira, Eanes Torres and Gomes, 
                         Herman Martins",
          affiliation = "UFCG and UFCG and UFCG and UFCG and UFCG and UFCG",
                title = "A Data Augmentation Methodology to Improve Age Estimation using 
                         Convolutional Neural Networks",
            booktitle = "Proceedings...",
                 year = "2016",
               editor = "Aliaga, Daniel G. and Davis, Larry S. and Farias, Ricardo C. and 
                         Fernandes, Leandro A. F. and Gibson, Stuart J. and Giraldi, Gilson 
                         A. and Gois, Jo{\~a}o Paulo and Maciel, Anderson and Menotti, 
                         David and Miranda, Paulo A. V. and Musse, Soraia and Namikawa, 
                         Laercio and Pamplona, Mauricio and Papa, Jo{\~a}o Paulo and 
                         Santos, Jefersson dos and Schwartz, William Robson and Thomaz, 
                         Carlos E.",
         organization = "Conference on Graphics, Patterns and Images, 29. (SIBGRAPI)",
            publisher = "IEEE Computer Society´s Conference Publishing Services",
              address = "Los Alamitos",
             keywords = "data augmentation, age estimation, deep learning, fiducial points, 
                         face detection.",
             abstract = "Recent advances in deep learning methodologies are enabling the 
                         construction of more accurate classifiers. However, existing 
                         labeled face datasets are limited in size, which prevents CNN 
                         models from reaching their full generalization capabilities. A 
                         variety of techniques to generate new training samples based on 
                         data augmentation have been proposed, but the great majority is 
                         limited to very simple transformations. The approach proposed in 
                         this paper takes into account intrinsic information about human 
                         faces in order to generate an augmented dataset that is used to 
                         train a CNN, by creating photo-realistic smooth face variations 
                         based on Active Appearance Models optimized for human faces. An 
                         experimental evaluation taking CNN models trained with original 
                         and augmented versions of the MORPH face dataset allowed an 
                         increase of 10% in the F-Score and yielded Receiver Operating 
                         Characteristic curves that outperformed state-of-the-art work in 
                         the literature.",
  conference-location = "S{\~a}o Jos{\'e} dos Campos, SP, Brazil",
      conference-year = "4-7 Oct. 2016",
                  doi = "10.1109/SIBGRAPI.2016.021",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI.2016.021",
             language = "en",
                  ibi = "8JMKD3MGPAW/3M5KU35",
                  url = "http://urlib.net/ibi/8JMKD3MGPAW/3M5KU35",
           targetfile = "PID4374341.pdf",
        urlaccessdate = "2024, May 01"
}