Segmentation and Recognition of Petroglyphs Using Generic Fourier Descriptors

Abstract

In this paper we present an approach for the segmentation and recognition of petroglyphs from images of rock art reliefs. To identify symbols we use a shape descriptor derived by 2-D Fourier transform, which is independent to scale and rotation, and robust to shape deformations. The efficacy of the algorithm has been validated by testing it with scenes and test images extracted from the archeological site located in Mount Bego (France). The results have been compared with those obtained by other descriptors

Interactive segmentation of rock-art in high-resolution 3D reconstructions

“…In the second step, they use an image deformation model to classify petroglyph shapes. Subsequently, Deufemia et al [7] use Fourier descriptors to detect and classify petroglyphs from full scenes which stem from manual tracings. Seidl et al [18], [17] combine skeletal descriptors with shape descriptors for petroglyph classification.…”

“…Deufemia and Paolino [7] apply segmentation to digitized manual tracings. This is a rather straight-forward task since manual tracings are binary images that already represent a manual pre-segmentation of the figures.…”

“…Existing work on the automated analysis of rock-art deals mostly with the recognition and classification of pre-segmented petroglyph shapes [23], [24], [8], [6], [7], [18], [17]. The automatic segmentation of petroglyph shapes is an important pre-processing step in this context which is still unsolved and even considered infeasible by Zhu et al [23].…”

“…Only a few works on the segmentation of petroglyph shapes exist. For instance, Deufemia et al [7] use the manual tracings (as shown in Fig. 1) as input for segmentation.…”

Agent‐oriented and ontology‐driven digital libraries: the IndianaMAS experience

“…Apart from our previous publications on the IndianaMAS architecture , on the image recognition algorithms used there , and on their exploitation in visual analytics and volunteered geographic information systems , few proposals address the problem of digital rock art classification and storage following an integrated approach where images, tracings, manual sketches, and multilingual texts are all considered relevant DOs and are managed in a homogeneous and consistent way.…”