Shape descriptors for non-rigid shapes with a single closed contour

TLDR

The CE‑Shape‑1 experiment for MPEG‑7 offered a rare chance to compare shape descriptors for non‑rigid shapes with a single closed contour, but prior studies were often biased by the favoring institute and a purely theoretical comparison is extremely difficult. This paper reports on the MPEG‑7 Core Experiment CE‑Shape. The experiment was performed by each descriptor’s supporting institute with optimally tuned parameters and thoroughly tested implementations, enabling a fair comparison across descriptors derived from diverse mathematical approaches.

Abstract

The Core Experiment CE-Shape-1 for shape descriptors performed for the MPEG-7 standard gave a unique opportunity to compare various shape descriptors for non-rigid shapes with a single closed contour. There are two main differences with respect to other comparison results reported in the literature: (1) For each shape descriptor the experiments were carried out by an institute that is in favor of this descriptor. This implies that the parameters for each system were optimally determined and the implementations were thoroughly rested. (2) It was possible to compare the performance of shape descriptors based on totally different mathematical approaches. A more theoretical comparison of these descriptors seems to be extremely hard. In this paper we report on the MPEG-7 Core Experiment CE-Shape.