Novel Automated Method for Minirhizotron Image Analysis: Root Detection using Curvelet Transform

In this article a new method is introduced for distinguishing roots and background based on theirdigital curvelet transform in minirhizotron images. In the proposed method, the nonlinear mapping isapplied to sub-band curvelet components followed by boundary detection using energy optimizationconcept. The curvelet transform has the excellent capability in detecting roots with differentorientations and contrasts, thanks to its better sparse representation and more directionality feature thanexisting approaches. Furthermore, adapting the parameters of the mapping function due to curveletcoefficients is very beneficial for magnifying weak ridges as well as better compatibility with differentminirhizotron images. Performance of the proposed method is evaluated on several minirhizotronimages in two different scenarios. In the first scenario, images contain several roots, while the secondscenario belongs to no-root images, which increases the chance of false detections. The results showthat the detection rate of the proposed method is 4 to 27 percent better than its alternatives, in presenceof zero false detection. Furthermore, it is shown that better characterization of roots by proposedalgorithm does not lead to extract more false objects compared to the results of the other examinedalgorithms.