Root crown detection using statistics of Zernike moments

In this paper an automatic method for detecting root crowns in root images for plants growing in gellan gum is proposed. In the proposed approach statistics of Zernike moments (ZMs) are used to model the bi-level root crown images and non root crown images. Bi-level image are generated by a process of normalization and segmentation. The statistics of the ZMs for the classes of root crowns and non root crowns are learnt from a labelled training data set. For classification of a new image patch into a root crown or non root crown class, a likelihood is computed assuming the orthogonal ZMs to be independent and normally distributed. The ratio of these two class likelihoods is used for classification. The results of classification are quantitatively analysed using Receiver Operating Characteristic (ROC) curves. The area under the ROC curve is used for deciding the order of ZMs to be used for detection of the root crowns. We evaluate the results of the proposed methodology both quantitatively and qualitatively. Results of root crown detection on real different plant roots are shown.