Petroglyph Classification using the Image Distortion Model

Petroglyphs are prehistoric engravings in stone unrevealing stories of ancient life and describing a conception of the world transmitted till today. The great number of sites and the high variability in the artifacts makes their study a very complex task. Thus, the development of tools which automate the recognition of petroglyphs is essential not only for supporting archaeologist to understand petroglyph symbols and relationships, but also for the anthropol-ogists who are interested in the evolution of human beings. However, many challenges exist in the recognition of petroglyph reliefs mainly due to their high level of distortion and variability. To address these challenges, in this paper we present an automatic image-based petroglyph recognizer that focuses on the visual appearance of the petroglyph in order to assess the similarity of petroglyph reliefs. The proposed matching algorithm is based on an image deformation model that is computationally efficient and robust to local distortions. The classification system has been applied to an image database containing 17 classes of petroglyph symbols from Mount Bego rock art site achieving a classification rate of 68%.

[1]  Shinji Mizuno,et al.  Shape Analysis of Petroglyphs in Central Asia , 2006 .

[2]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[3]  Salvatore Tabbone,et al.  Musings on Symbol Recognition , 2005, GREC.

[4]  H. Ney,et al.  Modeling Image Variability in Appearance-Based Gesture Recognition , 2006 .

[5]  Heiko Schuldt,et al.  Improving efficiency and effectiveness of the image distortion model , 2008, Pattern Recognit. Lett..

[6]  Viviana Mascardi,et al.  Rock Art Interpretation within Indiana MAS , 2012, KES-AMSTA.

[7]  Viviana Mascardi,et al.  Agents and Ontologies for Understanding and Preserving the Rock Art of Mount Bego , 2018, ICAART.

[8]  Hermann Ney,et al.  Deformation Models for Image Recognition , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Eamonn J. Keogh,et al.  Augmenting the generalized hough transform to enable the mining of petroglyphs , 2009, KDD.

[10]  Christian Breiteneder,et al.  Detection and Classification of Petroglyphs in Gigapixel Images - Preliminary Results , 2011, VAST.

[11]  K. I. Tashbaeva,et al.  Petroglyphs of Central Asia , 2001 .

[12]  Viviana Mascardi,et al.  Investigative analysis across documents and drawings: visual analytics for archaeologists , 2012, AVI.

[13]  Hermann Ney,et al.  Local context in non-linear deformation models for handwritten character recognition , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[14]  Hermann Ney,et al.  FIRE in ImageCLEF 2005: Combining Content-based Image Retrieval with Textual Information Retrieval , 2005, CLEF.

[15]  Christopher Chippindale.  Clarence Bicknell: archaeology and science in the 19th century , 1984, Antiquity.

[16]  Ernest Valveny,et al.  Symbol Recognition: Current Advances and Perspectives , 2001, GREC.

[17]  Viviana Mascardi,et al.  An agent-based framework for sketched symbol interpretation , 2008, J. Vis. Lang. Comput..

[18]  Eamonn J. Keogh,et al.  An efficient and effective similarity measure to enable data mining of petroglyphs , 2010, Data Mining and Knowledge Discovery.

[19]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.