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 (10 4 instances). An approach on how to optimally design the scatter transform based on energy contrast is provided. This is illustrated on the hard and open problem of weed detection in culture crops of high density from the top view in intensity images. An annotated synthetic data-set available under the form of a data challenge and a simulator are proposed for reproducible science. Scatter transform only trained on synthetic data shows an accuracy of 85% when tested on real data.3 of 16 the weeds included in the data-set Figure 3 are much more indented. Therefore, this computer vision problem is well adapted to test scatter transform which is a texture-based technique.
Camera
High density cropRemote Sens. 2019, 11, 249 7 of 16 no other anatomical items larger than the leaf itself. The number of layers tested was up to M = 4 as proposed in [3] since the energy after some layers although none zero is logically vanishing.Interestingly, these specific properties of the scatter transform match the intrinsic multiscale textural 127 nature of our weed detection problem which therefore constitutes an appropriate use case to assess 128 the potential of the scatter transform in practice. A visualization of output images for various filter 129 scale j at m = 2 for a given orientation is shown in Fig. 7. It clearly appears in Fig. 7 that the various 130 scales (texture of the limb and veins at j=3, border shape at j=4 and global leaf shape at j=8-not shown) 131 presented in section 2.2 can be captured with the different scaling factor applied on the wavelet. In our 132 study, we empirically picked L = 8 orientations and investigated up to J = 8 scales since there are 133 no other anatomical items larger than the leaf itself. The number of layers tested was up to M = 4 as 134 proposed in [3] since the energy after some layers although none zero is logically vanishing.
135
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.