An efficient and effective similarity measure to enable data mining of petroglyphs

Abstract

Rock art is an archaeological term for human-made markings on stone, including carved markings, known as petroglyphs, and painted markings, known as pictographs. It is believed that there are millions of petroglyphs in North America alone, and the study of this valued cultural resource has implications even beyond anthropology and history. Surprisingly, although image processing, information retrieval and data mining have had a large impact on many human endeavors, they have had essentially zero impact on the study of rock art. In this work we identify the reasons for this, and introduce a novel distance measure and algorithms which allow efficient and effective data mining of large collections of rock art.

A knowledge discovery process for spatiotemporal data: Application to river water quality monitoring

“…In order to get a clear view of data, patterns should be classified or clustered so that semantically similar terms are grouped together. Similarity measures such as Edit distance [22] and LCS [23] have been proposed in literature and have been applied in many contexts [24,25,26]. The measure S 2 M P proposed in [27] has been adopted in this work due to its effectiveness and its applicability to sequences of itemsets (see Section 3.3).…”

A volunteered geographic information system for collecting and rating petroglyph data

“…However, such analysis would never be complete without the contributions of volunteers, due to the amount of necessary work, and to technological limits, especially in the image processing domain. Indeed, although in the recent years several image recognition approaches have been proposed for automating the segmentation and classification of petroglyphs [15,16,10], their accuracy is still not fully satisfactory.…”

“…Unfortunately, there is no robust, automatic segmentation algorithm capable of determining the exact shapes and spatial locations of petroglyphs from rock art pictures [10]. In particular, the exact boundaries of petroglyphs are hard to identify, also due to the direction of the light [16].…”

“…CAPTCHA-ROCK is a system for helping archeologists to extract data from petroglyph images [10]. In particular, users have to trace petroglyph images with the mouse pointer for access control purposes.…”

“…In particular, the user provided information gathered by PetroAdvisor consists of petroglyph pictures, their contours, descriptions, comments, ratings, georeferenced information, and so forth. This way of collecting data not only reduces the necessity of man power, but it also allows archeologists to tackle several technology shortfalls, such as the automatic segmentation and identification of petroglyphs within pictures [10].…”