TY  - CONF
AU  - Juan A. Carvajal Ayala
AU  - Dennis Romero
AU  - Angel Sappa
A2  - CIARP
PY  - 2016//
TI  - Fine-tuning based deep convolutional networks for lepidopterous genus recognition
T2  - LNCS
BT  - 21st Ibero American Congress on Pattern Recognition
SP  - 467
EP  - 475
N2  - 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%.
L1  - http://refbase.cvc.uab.es/files/CRS2016.pdf
UR  - http://dx.doi.org/10.1007/978-3-319-52277-7_57
N1  - ADAS; 600.086
ID  - Juan A. Carvajal Ayala2016
ER  -