Hieroglyph retrieval has emerged as a tool to facilitate and support the cultural heritage preservation. For this task, hieroglyphs should be represented according its visual content. In the literature, the Bag of Visual Words (BoVW) model has been widely used for representing hieroglyphs with retrieval purposes. One crucial step in the BoVW model consists in replacing each local descriptor, obtained from a hieroglyph, by its nearest visual word in the vocabulary. However, it may result in similar local descriptors replaced by different visual words. Thus, the similarity of these local descriptors is lost. In this work, this problem is addressed by replacing each local descriptor by its k-nearest visual words in the vocabulary, instead of just one visual word (the nearest). Considering this multiple replacement, we introduce a hieroglyph representation that takes into account the frequency of the visual words and the co-occurrence of visual word pairs. Our experiments show that our proposed hieroglyph representation allows obtaining better retrieval results than those obtained by using state of the art representations.
SeidlM., WieserE. and Alexander.C., Automated classification of petroglyphs, Digital Applications in Archaeology and Cultural Heritage2(2-3) (2015), 196–212. ISSN 2212-0548. Digital imaging techniques for the study of prehistoric rock art.
2.
SeidlM., WieserE., ZeppelzauerM., PinzA., BreitenederC., Graph-Based Shape Similarity of Petroglyphs, Springer International Publishing, Cham, 2015, pp. 133–148.
3.
FrauelY., QuesadaO. and BribiescaE., Detection of a polymorphic mesoamerican symbol using a rule-based approach, Pattern Recognition39(7) (2006), 1380–1390. ISSN 0031-3203.
4.
ZhuangY., ZhangX., WuJ., LuX., Retrieval of Chinese Calligraphic Character Image, Springer Berlin Heidelberg, Berlin, Heidelberg, 2005, pp. 17–24. ISBN 978-3-540-30541-5.
5.
ZhuQ., WangX., KeoghE. and LeeS.-H., An efficient and effective similarity measure to enable data mining of petroglyphs, Data Mining and Knowledge Discovery23(1) (2011), 91–127. ISSN 1573-756X.
6.
Roman-RangelE., PallanC., OdobezJ.M. and Gatica-PerezD., Retrieving ancient maya glyphs with shape context, In 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, 2009, pp. 988–995.
7.
SivicJ. and ZissermanA., Video google: A text retrieval approach to object matching in videos, In Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2, ICCV ’03, Washington, DC, USA, 2003, p. 1470. IEEE Computer Society. ISBN 0-7695-1950-4.
8.
Roman-RangelE. and Marchand-MailletS., Bag-of-visualphrases via local contexts, In 2013 2nd IAPR Asian Conference on Pattern Recognition, 2013, pp. 867–871.
9.
DeufemiaV., PaolinoL. and LumleyH.D., Petroglyph recognition using self-organizing maps and fuzzy visual language parsing, In 2012 IEEE 24th International Conference on Tools with Artificial Intelligence, volume 1, 2012, pp. 852–859.
10.
DeufemiaV., PaolinoL., Combining Unsupervised Clustering with a Non-linear Deformation Model for Efficient Petroglyph Recognition, Springer Berlin Heidelberg, Berlin, Heidelberg, 2013, pp. 128–137. ISBN 978-3-642-41939-3.
11.
Roman-RangelE., PallanC., OdobezJ.-M. and Gatica-PerezD., Analyzing ancient maya glyph collections with contextual shape descriptors, International Journal of Computer Vision94(1) (2011), 101–117.
12.
Roman-RangelE., Pallan GayolC.,
OdobezJ.-M. and
Gatica-PerezD., Searching the past: An improved shape descriptor to retrieve maya hieroglyphs, In Proceedings of the 19th ACM International Conference on Multimedia, MM ’11, New York, NY, USA, 2011, pp. 163–172. ACM. ISBN 978-1-4503-0616-4.
13.
Roman-RangelE., Marchand-MailletS., HOOSC128: A More Robust Local Shape Descriptor, Springer International Publishing, Cham, 2014, pp. 172–181. ISBN 978-3-319-07491-7.
14.
FrankenM. and van GemertJ.C., Automatic egyptian hieroglyph recognition by retrieving images as texts, In Proceedings of the 21st ACM International Conference on Multimedia, MM’13, New York, NY, USA, 2013, pp. 765–768. ACM. ISBN 978-1-4503-2404-5.
15.
PaplińskiA.P., Rotation Invariant Categorization of Visual Objects Using Radon Transform and Self-Organizing Modules, Springer Berlin Heidelberg, Berlin, Heidelberg, 2010, pp. 360–366. ISBN 978-3-642-17534-3.
16.
MoriG., BelongieS. and MalikJ., Efficient shape matching using shape contexts, IEEE Trans Pattern Anal Mach Intell27(11) (2005), 1832–1837. ISSN 0162-8828, pp. 360–366.
17.
ShechtmanE. and IraniM., Matching local self-similarities across images and videos, In 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007, pp. 1–8.
18.
MikolajczykK. and SchmidC., Scale & affine invariant interest point detectors, International Journal of Computer Vision60(1) (2004), 63–86. ISSN 1573-1405.
19.
Roman-RangelE. and Marchand-MailletS., Stopwords detection in bag-of-visual-words: The case of retrieving maya hieroglyphs, In
PetrosinoA.,
MaddalenaL. and PalaP., editors, New Trends in Image Analysis and Processing – ICIAP 2013, Berlin, Heidelberg, Springer Berlin Heidelberg2013, pp. 159–168. ISBN 978-3-642-41190-8.
20.
LazebnikS., SchmidC. and PonceJ., Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories, In 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), volume 2, 2006, pp. 2169–2178.
21.
ZhangE. and MayoM., Improving bag-of-words model with spatial information, In 2010 25th International Conference of Image and Vision Computing New Zealand, 2010, pp. 1–8.
22.
Roman-RangelE., OdobezJ.-M., Gatica-PerezD., Evaluating Shape Descriptors for Detection of Maya Hieroglyphs, Springer Berlin Heidelberg, Berlin, Heidelberg, 2013, pp. 145–154. ISBN 978-3-642-38989-4.
23.
VincentL., Morphological area openings and closings for grey-scale images. In
OY.-L.,
ToetA.,
FosterD.,
HeijmansH.J.A.M. and
MeerP., editors, Shape in Picture, Berlin, Heidelberg, Springer Berlin Heidelberg, 1994, pp. 197–208. ISBN 978-3-662-03039-4.
24.
GuoJ., WangC., Roman-RangelE., ChaoH. and RuiY., Building hierarchical representations for oracle character and sketch recognition, IEEE Transactions on Image Processing25(1) (2016), 104–118.
25.
LamL., LeeS.-W. and SuenC.Y., Thinning methodologies-a comprehensive survey, IEEE Trans Pattern Anal Mach Intell14(9) (1992), 869–885. ISSN 0162-8828.
26.
Roman-RangelE. and Marchand-MailletS., Shape-based detection of maya hieroglyphs using weighted bag representations, Pattern Recognition48(4) (2015), 1161–1173. ISSN 0031-3203.
27.
LoweD.G., Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision60(2) (2004), 91–110.
