Drums and Curve Descriptors

Abstract

In this paper we present a new physically motivated curve descriptor based on the solution of Helmholtz's equation. The descriptor satisfies the six principles set by MPEG-7: it has a good retrieval accuracy, it is compact, it can be applied in general contexts, it has a reasonable computational complexity, it is robust and provides an hierarchical representation of the curve from coarse to fine. Moreover this descriptor generalizes straightforwardly to three dimensional surfaces. We tested the performance of the descriptor in the context of affine invariant curve matching using the multiview curve dataset (MCD), which consists of 40 curves (extracted from the MPEG-7 shape dataset) imaged under 14 different points of view. The results we obtained show that the proposed descriptor satisfies the MPEG-7 requirements and presents some advantages over some of the commonly used curve descriptors.

A New Histogram-Based Descriptor for Images Retrieval from Databases

“…The Recall-Precision graph indicates more than 91.86% Recall for more than 92% Precision for the proposed approach. This outperforms the reported performance that are 86% Recall for 85% Precision for Helmholtz curve descriptor (HCD) [11] and 90% Recall for 90% Precision obtained by Ekombo et al with the invariant Fourier descriptor [3]. …”

“…C -MCD dataset: Figure 10 shows the Precision vs. Recall graphs obtained from the MCD database. Compared to the results reported in recent studies [3] and [11], the proposed approach performs very well. The Recall-Precision graph indicates more than 91.86% Recall for more than 92% Precision for the proposed approach.…”

“…In order to compare our results with those from other methods, the experiments are done on three well-known databases that are the kimia99 dataset [8], the multiview curve dataset (MCD) [10], [11] and that extracted from the SQUID marine animals [12]. The performance of the descriptors is evaluated using the Precision-Recall curve averaged over the whole database and particularly we present the bull's eye performance (BEP).…”

Herbal Leave Recognition System Based on Dirichlet Laplacian Eigenvalues

“…All three features are obviously size-invariant [4]. The F 1 features were first proposed by Zuliani et al [12]. The values of F 1 (Ω) and F 2 (Ω) are in the unit cube, while those of F 3 (Ω) are between ±1 a useful range when using neural networks.…”

“…For a given binary image Ω, ( [12] and [4]) proposed the following three feature sets based on the above described eigenvalues…”