Artículos de revistas
Deep learning for plant identification using vein morphological patterns
Fecha
2016-09Registro en:
Grinblat, Guillermo Luis; Uzal, Lucas César; Larese, Monica Graciela; Granitto, Pablo Miguel; Deep learning for plant identification using vein morphological patterns; Elsevier; Computers and Eletronics in Agriculture; 127; 9-2016; 418-424
0168-1699
CONICET Digital
CONICET
Autor
Grinblat, Guillermo Luis
Uzal, Lucas César
Larese, Monica Graciela
Granitto, Pablo Miguel
Resumen
We propose using a deep convolutional neural network (CNN) for the problem of plant identification from leaf vein patterns. In particular, we consider classifying three different legume species: white bean, red bean and soybean. The introduction of a CNN avoids the use of handcrafted feature extractors as it is standard in state of the art pipeline. Furthermore, this deep learning approach significantly improves the accuracy of the referred pipeline. We also show that the reported accuracy is reached by increasing the model depth. Finally, by analyzing the resulting models with a simple visualization technique, we are able to unveil relevant vein patterns.