Perceptually motivated shape context which uses shape interiors

In this paper, we identify some of the limitations of current-day shape-matching techniques. We provide examples of how contour-based shape-matching techniques cannot provide a good match for certain visually similar shapes. To overcome this limitation, we propose a perceptually motivated variant of the well-known shape context descriptor. We identify that the interior properties of the shape play an important role in object recognition and develop a descriptor that captures these interior properties. We show that our method can easily be augmented with any other shape-matching algorithm. We also show from our experiments that the use of our descriptor can significantly improve the retrieval rates.

► We suggest a need for non-contour-based shape-matching techniques. ► We propose a perceptually motivated variant of the well-known shape context descriptor. ► We present a new and simple technique for sampling points from within a shape. ► We identify the advantages of using a shape's convex hull as landmark locations. ► We show good shape retrieval performance on a widely used shape database.