Robust thinning algorithm without artefacts for pattern recognition and 3D plant modelling

We present a novel thinning algorithm to automatically extract skeletons from images without artefacts. It is well known that the major problem of existing thinning algorithms is the generation of artefacts such redundant branches due to noises in images. In this approach, we propose to use oriented Gaussian filters to classify ridges and edges, and to determine principal directions. As oriented filters are low-pass filters in the principal directions, they are robust to noise and insignificant extremities. The thinning process of the proposed algorithm is guided by principal directions, thus it can remove edge points without the interference from noise and insignificant extremities. As a result, the extracting skeletons of elongated shapes is smooth and without redundant branches. Experimental results show that the proposed approach is able to handle noise and insignificant extremities to generate smooth skeletons of objects, and also is able to automatically extract 3D structures of cereal plants.