Weed leaf image segmentation by deformable templates

In order to improve weeding strategies in terms of pesticide reduction, spa tial distribution and characterization of in-field weed populations are imp ortant. With recent improvements in image processing, many studies have foc used on weed detection by vision techniques. However, weed identification s till remains difficult because of outdoor scenic complexity and morphologic al variability of plants. A new method of weed leaf segmentation based on the use of deformable templ ates is proposed. This approach has the advantage of applying a priori know ledge to the object searched, improving the robustness of the segmentation stage. The principle consists of fitting a parametric model to the leaf out lines in the image, by minimizing an energy term related to internal constr aints of the model and salient features of the image, such as the colour of the plant. This method showed promising results for one weed species, green foxtail (S etaria viridis). In particular, it was possible to characterize partially o ccluded leaves. This constitutes a first step towards a recognition system, based on leaf characteristics and their relative spatial position. (C) 200 1 Silsoe Research Institute.