Remote Sensing | 卷:11 |
Supervised Image Classification by Scattering Transform with Application to Weed Detection in Culture Crops of High Density | |
Etienne Belin1  Pejman Rasti1  Ali Ahmad1  Salma Samiei1  David Rousseau1  | |
[1] LARIS, UMR INRA IRHS, Université d’Angers, 62 avenue Notre Dame du Lac, 49000 Angers, France; | |
关键词: weed detection; scatter transform; deep learning; machine-learning classification; annotation; synthetic data; local binary pattern; | |
DOI : 10.3390/rs11030249 | |
来源: DOAJ |
【 摘 要 】
In this article, we assess the interest of the recently introduced multiscale scattering transform for texture classification applied for the first time in plant science. Scattering transform is shown to outperform monoscale approaches (gray-level co-occurrence matrix, local binary patterns) but also multiscale approaches (wavelet decomposition) which do not include combinatory steps. The regime in which scatter transform also outperforms a standard CNN architecture in terms of data-set size is evaluated (
【 授权许可】
Unknown