The Peruvian Amazon Forestry Dataset: A Leaf Image Classification Corpus (Papers Track) Spotlight

Gerson Waldyr Vizcarra Aguilar (San Pablo Catholic University); Danitza Bermejo (Universidad Nacional del Altiplano); Manasses A. Mauricio (Universidad Católica San Pablo); Ricardo Zarate (Instituto de Investigaciones de la Amazonía Peruana); Erwin Dianderas (Instituto de Investigaciones de la Amazonía Peruana)

Slides PDF Recorded Talk Cite
Meta- and Transfer Learning Forests

Abstract

This paper introduces the Peruvian Amazon Forestry Dataset, which includes 59,441 leaves samples from ten of the most profitable and endangered Amazon timber-tree species. Besides, the proposal includes a background removal algorithm to feed a fine-tuned CNN. We evaluate the quantitative (accuracy metric) and qualitative (visual interpretation) impacts of each stage by ablation experiments. The results show a 96.64 % training accuracy and 96.52 % testing accuracy on the VGG-19 model. Furthermore, the visual interpretation of the model evidences that leaf venations have the highest correlation in the plant recognition task.

Recorded Talk (direct link)

Loading…