10 Extracting Maya Glyphs from Degraded Ancient Documents via Image Segmentation RUI HU, Idiap Research Institute JEAN-MARC ODOBEZ and DANIEL GATICA-PEREZ, Idiap Research Institute and ´ Ecole Polytechnique F´ ed´ erale de Lausanne (EPFL) We present a system for automatically extracting hieroglyph strokes from images of degraded ancient Maya codices. Our system adopts a region-based image segmentation framework. Multi-resolution super-pixels are first extracted to represent each image. A Support Vector Machine (SVM) classifier is used to label each super-pixel region with a probability to belong to foreground glyph strokes. Pixelwise probability maps from multiple super-pixel resolution scales are then aggregated to cope with various stroke widths and background noise. A fully connected Conditional Random Field model is then applied to improve the labeling consistency. Segmentation results show that our system preserves delicate local details of the historic Maya glyphs with various stroke widths and also reduces background noise. As an application, we conduct retrieval experiments using the extracted binary images. Experimental results show that our automatically extracted glyph strokes achieve comparable retrieval results to those obtained using glyphs manually segmented by epigraphers in our team. CCS Concepts:  Computing methodologies → Image segmentation; Visual content-based indexing and retrieval; Image representations;  Applied computing → Arts and humanities; Additional Key Words and Phrases: Ancient maya codices, document binarization, hieroglyph retrieval ACM Reference Format: Rui Hu, Jean-Marc Odobez, and Daniel Gatica-Perez. 2017. Extracting maya glyphs from degraded ancient documents via image segmentation. ACM J. Comput. Cult. Herit. 10, 2, Article 10 (March 2017), 22 pages. DOI: http://dx.doi.org/10.1145/2996859 1. INTRODUCTION The ancient Maya language infused art with unique pictorial forms of hieroglyphic writing and has left us an exceptionally rich legacy of the ancient Maya civilization. Most Maya texts were produced during the classic period of the ancient Mayan civilization (AD 250–900), throughout which hiero- glyphic texts were carved or painted on various media types, including stone monuments, personal items, and so on. A special type of Maya text was discovered written on screenfold books (the so-called This work is supported by the Swiss National Science Foundation (SNSF) through the project MAAYA: Multimedia Analysis and Access for Documentation and Decipherment of Maya Epigraphy. Authors’ addresses: Idiap Research Institute, Centre du Parc, Rue Marconi 19, 1920 Martigny, Switzerland; R. Hu, J.-M. Odobez, and D. Gatica-Perez; emails: {rhu, odobez, gatica}@idiap.ch. Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies show this notice on the first page or initial screen of a display along with the full citation. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, to republish, to post on servers, to redistribute to lists, or to use any component of this work in other works requires prior specific permission and/or a fee. Permissions may be requested from Publications Dept., ACM, Inc., 2 Penn Plaza, Suite 701, New York, NY 10121-0701 USA, fax +1 (212) 869-0481, or permissions@acm.org. c  2017 ACM 1556-4673/2017/03-ART10 $15.00 DOI: http://dx.doi.org/10.1145/2996859 ACM Journal on Computing and Cultural Heritage, Vol. 10, No. 2, Article 10, Publication date: March 2017.