Unverified paper record
Regression in Convolutional Neural Networks applied to Plant Leaf Counting
Anais do XV Workshop de Visão Computacional (WVC 2019) · 9 Sept 2019 · 10.5753/wvc.2019.7627
Abstract
Recent studies have shown that computer vision techniques developed to boost the count of plant leaves brings significant improvements. In this paper, a proposal was presented for plant leaf counting using Convolutional Neural Networks (CNNs). To accomplish the training process, CNNs architectures were adapted to solve regression problems. To evaluate the proposed method, an image dataset with 810 images of three species (Arabidopsis, Tobacco and one mutation) was used. The results showed that Xception architecture obtained the best results with R2 of 0.96 and MAE (mean absolute error) of 0.46.
Plant phenotyping relevance
CNNを用いた植物葉数の画像ベース推定手法を提案し、複数アーキテクチャとデータセットで性能評価しており、表現型取得・抽出法が研究の中心である。
abstractIn this paper, a proposal was presented for plant leaf counting using Convolutional Neural Networks (CNNs).
abstractTo evaluate the proposed method, an image dataset with 810 images of three species (Arabidopsis, Tobacco and one mutation) was used.
abstractThe results showed that Xception architecture obtained the best results with R2 of 0.96 and MAE (mean absolute error) of 0.46.
Code and data availability
The full-text asset investigation has not produced a conclusive result yet.
No evidence-backed public reproduction asset is currently recorded.
This is an automatically classified, unverified record. Curator approval is required before any resource enters the Catalog.