%0 Conference Proceedings
%T Fine-tuning based deep convolutional networks for lepidopterous genus recognition
%A Juan A. Carvajal Ayala
%A Dennis Romero
%A Angel Sappa
%B 21st Ibero American Congress on Pattern Recognition
%D 2016
%F Juan A. Carvajal Ayala2016
%O ADAS; 600.086
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2913), last updated on Tue, 21 Nov 2017 11:02:34 +0100
%X This paper describes an image classification approach oriented to identify specimens of lepidopterous insects at Ecuadorian ecological reserves. This work seeks to contribute to studies in the area of biology about genus of butterflies and also to facilitate the registration of unrecognized specimens. The proposed approach is based on the fine-tuning of three widely used pre-trained Convolutional Neural Networks (CNNs). This strategy is intended to overcome the reduced number of labeled images. Experimental results with a dataset labeled by expert biologists is presented, reaching a recognition accuracy above 92%.
%U http://refbase.cvc.uab.es/files/CRS2016.pdf
%U http://dx.doi.org/10.1007/978-3-319-52277-7_57
%P 467-475