Inner-Distance SC (IDSC) by replacing the Euclidean distance

In this paper, we propose a novel contour-based shape descriptor, named Multiscale Distance Matrix (MDM), to capture shape geometry while being invariant to translation, rotation, scaling, and bilateral symmetry. The descriptor is further combined with dimensionality reduction to improve its discriminative power. The proposed method avoids the time-consuming point-wise matching used in most of the previous shape recognition algorithms. It is therefore fast and suitable for real-time applications. We applied the proposed method to the task of plan leaf recognition with experiments on two datasets: the Swedish Leaf dataset and the ICL Leaf dataset. The experimental results demonstrate clearly the effectiveness and efficiency of the proposed descriptor.