Integral Contour Angle: An Invariant Shape Descriptor for Classification and Retrieval of Leaf Images

Abstract

Leaf identification is a significant and challenging task for computer vision community due to the large intra-class variations and small inter-class differences of leaf image patterns. In this paper, a novel shape descriptor, called Integral Contour Angle (ICA), is proposed for accurate classification and retrieval of leaf images. For a contour point, two bunches of vectors emanate from it and ends at its left neighbor contour points and its right neighbor ones respectively. Their average vectors form an angle (termed ICA) having inherent invariance to translation, rotation and scaling of leaf shape. Changing the size of the neighborhood of the contour point naturally yields a set of ICAs at different scales. Group them to form a multiscale descriptor (called mICA) for the contour point. Collect the mICAs of all the contour points to construct a mICA set. The dissimilarity between two leaf shapes is measured by calculating the enhanced Hausdorff distance between their mICA sets. The experiment results on two popular leaf image datasets indicate that the proposed method outperforms the state-of-the-art methods.