Using Deep Learning to Identify Costa Rican Native Tree Species From Wood Cut Images

Geovanni Figueroa-Mata; Erick Mata-Montero; Juan Carlos Valverde-Otárola; Dagoberto Arias-Aguilar; Nelson Zamora-Villalobos

doi:10.3389/fpls.2022.789227

Using Deep Learning to Identify Costa Rican Native Tree Species From Wood Cut Images

Front Plant Sci. 2022 Apr 1:13:789227. doi: 10.3389/fpls.2022.789227. eCollection 2022.

Authors

Geovanni Figueroa-Mata¹, Erick Mata-Montero², Juan Carlos Valverde-Otárola^{3

4}, Dagoberto Arias-Aguilar³, Nelson Zamora-Villalobos³

Affiliations

¹ School of Mathematics, Costa Rica Institute of Technology, Cartago, Costa Rica.
² School of Computing, Costa Rica Institute of Technology, Cartago, Costa Rica.
³ School of Forestry Engineering, Costa Rica Institute of Technology, Cartago, Costa Rica.
⁴ Cooperativa de Productividad Forestal, Facultad de Ciencias Forestales, Universidad de Concepción, Concepción, Chile.

Abstract

Tree species identification is critical to support their conservation, sustainable management and, particularly, the fight against illegal logging. Therefore, it is very important to develop fast and accurate identification systems even for non-experts. In this research we have achieved three main results. First, we developed-from scratch and using new sample collecting and processing protocols-an dataset called CRTreeCuts that comprises macroscopic cross-section images of 147 native tree species from Costa Rica. Secondly, we implemented a CNN for automated tree species identification based on macroscopic images of cross-sections of wood. For this CNN we apply the fine-tuning technique with VGG16 as a base model, pre-trained with the ImageNet data set. This model is trained and tested with a subset of 75 species from CRTreeCuts. The top-1 and top-3 accuracies achieved in the testing phase are 70.5% and 80.3%, respectively. The Same-Specimen-Picture Bias (SSPB), which is known to erroneously increase accuracy, is absent in all experiments. Finally, the third result is Cocobolo, an Android mobile application that uses the developed CNN as back-end to identify Costa Rican tree species from images of cross-sections of wood.

Keywords: automated image-based tree species identification; convolutional neural network; costa rican tree species; deep learning; plant classification; xylotheques.