research-article

Evaluating Shape Representations for Maya Glyph Classification

Authors:

Jean-Marc Odobez,

Daniel Gatica-PerezAuthors Info & Claims

Journal on Computing and Cultural Heritage (JOCCH), Volume 9, Issue 3

Article No.: 14, Pages 1 - 26

https://doi.org/10.1145/2905369

Published: 20 September 2016 Publication History

Abstract

Shape representations are critical for visual analysis of cultural heritage materials. This article studies two types of shape representations in a bag-of-words-based pipeline to recognize Maya glyphs. The first is a knowledge-driven Histogram of Orientation Shape Context (HOOSC) representation, and the second is a data-driven representation obtained by applying an unsupervised Sparse Autoencoder (SA). In addition to the glyph data, the generalization ability of the descriptors is investigated on a larger-scale sketch dataset. The contributions of this article are four-fold: (1) the evaluation of the performance of a data-driven auto-encoder approach for shape representation; (2) a comparative study of hand-designed HOOSC and data-driven SA; (3) an experimental protocol to assess the effect of the different parameters of both representations; and (4) bridging humanities and computer vision/machine learning for Maya studies, specifically for visual analysis of glyphs. From our experiments, the data-driven representation performs overall in par with the hand-designed representation for similar locality sizes on which the descriptor is computed. We also observe that a larger number of hidden units, the use of average pooling, and a larger training data size in the SA representation all improved the descriptor performance. Additionally, the characteristics of the data and stroke size play an important role in the learned representation.

References

[1]

Sebastiano Battiato, Giovanni Maria Farinella, Giovanni Gallo, and Daniele Ravì. 2010. Exploiting Textons distributions on spatial hierarchy for scene classification. Journal on Image and Video Processing 2010 (2010), 7.

Digital Library

[2]

Sebastiano Battiato, Giovanni Maria Farinella, Oliver Giudice, and Giovanni Puglisi. 2015. Aligning shapes for symbol classification and retrieval. Multimedia Tools and Applications (2015), 1--19.

Digital Library

[3]

Serge Belongie, Jitendra Malik, and Jan Puzicha. 2000. Shape context: A new descriptor for shape matching and object recognition. In Conference on Advances in Neural Information Processing Systems, Vol. 2. 3.

[4]

Yoshua Bengio and James S. Bergstra. 2009. Slow, decorrelated features for pretraining complex cell-like networks. In Conference on Advances in Neural Information Processing Systems 22. 99--107.

Digital Library

[5]

Yoshua Bengio, Aaron Courville, and Pascal Vincent. 2013. Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence 35, 8 (2013), 1798--1828.

Digital Library

[6]

Y.-L. Boureau, Francis Bach, Yann LeCun, and Jean Ponce. 2010. Learning mid-level features for recognition. In Conference on Computer Vision and Pattern Recognition. IEEE, 2559--2566.

[7]

K. Chatfield, V. Lempitsky, A. Vedaldi, and A. Zisserman. 2011. The devil is in the details: An evaluation of recent feature encoding methods. In British Machine Vision Conference.

[8]

L. Chen, F. Rottensteiner, and C. Heipke. 2015. Feature descriptor by convolution and pooling autoencoders. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 1 (2015), 31--38.

[9]

Adam Coates, Andrew Y. Ng, and Honglak Lee. 2011. An analysis of single-layer networks in unsupervised feature learning. In International Conference on Artificial Intelligence and Statistics. 215--223.

[10]

Navneet Dalal and Bill Triggs. 2005. Histograms of oriented gradients for human detection. In Conference on Computer Vision and Pattern Recognition, Vol. 1. IEEE, 886--893.

Digital Library

[11]

Mathias Eitz, James Hays, and Marc Alexa. 2012. How do humans sketch objects? ACM Transactions on Graphics (Proceedings SIGGRAPH) 31, 4 (2012), 44:1--44:10.

Digital Library

[12]

Sergio Escalera, Alicia Fornés, Oriol Pujol, Josep Lladós, and Petia Radeva. 2011. Circular blurred shape model for multiclass symbol recognition. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on 41, 2 (2011), 497--506.

Digital Library

[13]

Orhan Firat. 2015. libORF: A Machine Learning Toolkit for Deep Learning, Probabilistic Graphical Models and Structured Prediction. Available from: http://www.ceng.metu.edu.tr/e1697481/libORF.html. Accessed: 2015-06-03.

[14]

Morris Franken and Jan C. van Gemert. 2013. Automatic Egyptian hieroglyph recognition by retrieving images as texts. In ACM International Conference on Multimedia. ACM, 765--768.

Digital Library

[15]

Geoffrey E. Hinton and Richard S. Zemel. 1994. Autoencoders, minimum description length, and Helmholtz free energy. Conference on Advances in Neural Information Processing Systems (1994), 3--3.

Digital Library

[16]

Rui Hu, Gulcan Can, Carlos Pallan Gayol, Guido Krempel, Jakub Spotak, Gabrielle Vail, Stephane Marchand-Maillet, Jean-Marc Odobez, and Daniel Gatica-Perez. 2015. Multimedia analysis and access of ancient Maya epigraphy. Signal Processing Magazine 32, 4 (July 2015), 75--84.

[17]

Yangqing Jia, Chang Huang, and Trevor Darrell. 2012. Beyond spatial pyramids: Receptive field learning for pooled image features. In Conference on Computer Vision and Pattern Recognition. IEEE, 3370--3377.

Digital Library

[18]

P. D. Kovesi. 2015. MATLAB and Octave Functions for Computer Vision and Image Processing. Available from: http://www.peterkovesi.com/matlabfns/. Accessed: 2015-01-16.

[19]

Solomon Kullback and Richard A. Leibler. 1951. On information and sufficiency. The Annals of Mathematical Statistics 22, 1 (1951), 79--86.

[20]

Svetlana Lazebnik, Cordelia Schmid, and Jean Ponce. 2006. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In Conference on Computer Vision and Pattern Recognition, Vol. 2. IEEE, 2169--2178.

Digital Library

[21]

Biao Leng, Shuang Guo, Xiangyang Zhang, and Zhang Xiong. 2015. 3D object retrieval with stacked local convolutional autoencoder. Signal Processing 112 (2015), 119--128.

Digital Library

[22]

David G. Lowe. 1999. Object recognition from local scale-invariant features. In International Conference on Computer Vision, Vol. 2. Ieee, 1150--1157.

Digital Library

[23]

Martha J. Macri and Matthew George Looper. 2003. The New Catalog of Maya Hieroglyphs: The Classic Period Inscriptions. Vol. 1. University of Oklahoma Press.

[24]

Andrew Ng. 2013. Sparse Autoencoders Lecture Notes. https://web.stanford.edu/class/cs294a/sparseAutoencoder.pdf. (2013). Accessed: 2015-07-30.

[25]

Jiquan Ngiam, Adam Coates, Ahbik Lahiri, Bobby Prochnow, Quoc V. Le, and Andrew Y. Ng. 2011. On optimization methods for deep learning. In International Conference on Machine Learning. 265--272.

[26]

Florent Perronnin, Jorge Sánchez, and Thomas Mensink. 2010. Improving the Fisher kernel for large-scale image classification. In European Conference on Computer Vision. Springer, 143--156.

Digital Library

[27]

Marc Aurelio Ranzato, Fu Jie Huang, Y.-Lan Boureau, and Yann LeCun. 2007. Unsupervised learning of invariant feature hierarchies with applications to object recognition. In Conference on Computer Vision and Pattern Recognition. IEEE, 1--8.

[28]

Edgar Roman-Rangel. 2012. Statistical Shape Descriptors for Ancient Maya Hieroglyphs Analysis. Ph.D. Dissertation. École Polytechnique Fédérale de Lausanne.

[29]

Edgar Roman-Rangel, Jean-Marc Odobez, and Daniel Gatica-Perez. 2012. Assessing sparse coding methods for contextual shape indexing of Maya hieroglyphs. Journal of Multimedia 7, 2 (April 2012), 179--192.

[30]

Edgar Roman-Rangel, Jean-Marc Odobez, and Daniel Gatica-Perez. 2013. Evaluating shape descriptors for detection of Maya hieroglyphs. In Mexican Conference on Pattern Recognition.

[31]

Edgar Roman-Rangel, Carlos Pallan, Jean-Marc Odobez, and Daniel Gatica-Perez. 2011. Analyzing ancient Maya glyph collections with contextual shape descriptors. International Journal of Computer Vision 94, 1 (2011), 101--117.

Digital Library

[32]

Hoo-Chang Shin, Matthew R. Orton, David J. Collins, Simon J. Doran, and Martin O. Leach. 2013. Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4D patient data. IEEE Transactions on Pattern Analysis and Machine Intelligence 35, 8 (2013), 1930--1943.

Digital Library

[33]

Josef Sivic and Andrew Zisserman. 2003. Video google: A text retrieval approach to object matching in videos. In International Conference on Computer Vision. IEEE, 1470--1477.

Digital Library

[34]

John Eric Sidney Thompson and George E. Stuart. 1962. A Catalog of Maya Hieroglyphs. University of Oklahoma Press Norman.

[35]

Jan C. van Gemert, Jan-Mark Geusebroek, Cor J. Veenman, and Arnold W. M. Smeulders. 2008. Kernel codebooks for scene categorization. In European Conference on Computer Vision. Springer, 696--709.

Digital Library

[36]

Jinjun Wang, Jianchao Yang, Kai Yu, Fengjun Lv, Thomas Huang, and Yihong Gong. 2010. Locality-constrained linear coding for image classification. In Conference on Computer Vision and Pattern Recognition. IEEE, 3360--3367.

[37]

Meng Wang, Youbin Chen, and Xingjun Wang. 2014. Recognition of handwritten characters in Chinese legal amounts by stacked autoencoders. In International Conference on Pattern Recognition. IEEE, 3002--3007.

Digital Library

[38]

Guo-Sen Xie, Xu-Yao Zhang, and Cheng-Lin Liu. 2015. Efficient feature coding based on auto-encoder network for image classification. In Asian Conference on Computer Vision. Springer, 628--642.

[39]

Matthew D. Zeiler. 2012. ADADELTA: An adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012).

[40]

Xi Zhou, Kai Yu, Tong Zhang, and Thomas S. Huang. 2010. Image classification using super-vector coding of local image descriptors. In European Conference on Computer Vision. Springer, 141--154.

Digital Library

Cited By

Malinverni EAbate DAgapiou AStefano FFelicetti APaolanti MPierdicca RZingaretti P(2024)SIGNIFICANCE deep learning based platform to fight illicit trafficking of Cultural Heritage goodsScientific Reports10.1038/s41598-024-65885-614:1Online publication date: 2-Jul-2024
https://doi.org/10.1038/s41598-024-65885-6
Chapinal-Heras DDíaz-Sánchez C(2024)A review of AI applications in human sciences researchDigital Applications in Archaeology and Cultural Heritage10.1016/j.daach.2024.e0032332(e00323)Online publication date: Mar-2024
https://doi.org/10.1016/j.daach.2024.e00323
Sommerschield TAssael YPavlopoulos JStefanak VSenior ADyer CBodel JPrag JAndroutsopoulos Ide Freitas N(2023)Machine Learning for Ancient Languages: A SurveyComputational Linguistics10.1162/coli_a_0048149:3(703-747)Online publication date: 1-Sep-2023
https://doi.org/10.1162/coli_a_00481
Show More Cited By

Index Terms

Evaluating Shape Representations for Maya Glyph Classification
1. Applied computing
  1. Arts and humanities
2. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision representations
        Shape representations
  2. Machine learning
    1. Machine learning approaches
      1. Neural networks

Recommendations

Analyzing Ancient Maya Glyph Collections with Contextual Shape Descriptors

This paper presents an original approach for shape-based analysis of ancient Maya hieroglyphs based on an interdisciplinary collaboration between computer vision and archeology. Our work is guided by realistic needs of archaeologists and scholars who ...
Shape Representations for Maya Codical Glyphs: Knowledge-driven or Deep?
CBMI '17: Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing

This paper investigates two-types of shape representations for individual Maya codical glyphs: traditional bag-of-words built on knowledge-driven local shape descriptors (HOOSC), and Convolutional Neural Networks (CNN) based representations, learned ...
Medical image classification via multiscale representation learning

Multiscale representation learning method is used to capture the intrinsic scales.Fisher vector technique is used to encode the extracted features.A fixed-length image representation is obtained regardless of the input size.Providing more abundant ...

Comments

Information & Contributors

Information

Published In

cover image Journal on Computing and Cultural Heritage

Journal on Computing and Cultural Heritage Volume 9, Issue 3

November 2016

136 pages

ISSN:1556-4673

EISSN:1556-4711

DOI:10.1145/2999571

Editor:
Roberto Scopigno
CNR ISTI, Italy

Issue’s Table of Contents

Copyright © 2016 ACM.

Permission to make digital or hard copies of all or part 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 bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 20 September 2016

Accepted: 01 March 2016

Revised: 01 March 2016

Received: 01 August 2015

Published in JOCCH Volume 9, Issue 3

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed

Funding Sources

Swiss National Science Foundation (SNSF) through the MAAYA project (Multimedia Analysis and Access for Documentation and Decipherment of Maya Epigraphy)

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

14
Total Citations
View Citations
225
Total Downloads

Downloads (Last 12 months)16
Downloads (Last 6 weeks)1

Reflects downloads up to 31 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Malinverni EAbate DAgapiou AStefano FFelicetti APaolanti MPierdicca RZingaretti P(2024)SIGNIFICANCE deep learning based platform to fight illicit trafficking of Cultural Heritage goodsScientific Reports10.1038/s41598-024-65885-614:1Online publication date: 2-Jul-2024
https://doi.org/10.1038/s41598-024-65885-6
Chapinal-Heras DDíaz-Sánchez C(2024)A review of AI applications in human sciences researchDigital Applications in Archaeology and Cultural Heritage10.1016/j.daach.2024.e0032332(e00323)Online publication date: Mar-2024
https://doi.org/10.1016/j.daach.2024.e00323
Sommerschield TAssael YPavlopoulos JStefanak VSenior ADyer CBodel JPrag JAndroutsopoulos Ide Freitas N(2023)Machine Learning for Ancient Languages: A SurveyComputational Linguistics10.1162/coli_a_0048149:3(703-747)Online publication date: 1-Sep-2023
https://doi.org/10.1162/coli_a_00481
Chapinal-Heras DDíaz-Sánchez C(2023)A review of AI applications in Human Sciences researchDigital Applications in Archaeology and Cultural Heritage10.1016/j.daach.2023.e0028830(e00288)Online publication date: Sep-2023
https://doi.org/10.1016/j.daach.2023.e00288
Melnik GYekutieli YSharf A(2022)Deep Segmentation of Corrupted GlyphsJournal on Computing and Cultural Heritage 10.1145/346562915:1(1-24)Online publication date: 22-Jan-2022
https://dl.acm.org/doi/10.1145/3465629
Assael YSommerschield TShillingford BBordbar MPavlopoulos JChatzipanagiotou MAndroutsopoulos IPrag Jde Freitas N(2022)Restoring and attributing ancient texts using deep neural networksNature10.1038/s41586-022-04448-z603:7900(280-283)Online publication date: 9-Mar-2022
https://doi.org/10.1038/s41586-022-04448-z
Cacciari IPocobelli G(2022)Machine Learning: A Novel Tool for ArchaeologyHandbook of Cultural Heritage Analysis10.1007/978-3-030-60016-7_33(961-1002)Online publication date: 1-Jan-2022
https://doi.org/10.1007/978-3-030-60016-7_33
Kumar POfli FImran MCastillo C(2020)Detection of Disaster-Affected Cultural Heritage Sites from Social Media Images Using Deep Learning TechniquesJournal on Computing and Cultural Heritage 10.1145/338331413:3(1-31)Online publication date: 16-Aug-2020
https://dl.acm.org/doi/10.1145/3383314
Flores FUgalde FDíaz JNavarro JGastelum-strozzi AAngeles MMiyatake M(2019)Computer Algorithm for Archaeological Projectile Points Automatic ClassificationJournal on Computing and Cultural Heritage 10.1145/330097212:3(1-30)Online publication date: 13-Jun-2019
https://dl.acm.org/doi/10.1145/3300972
Can GOdobez JGatica-Perez D(2018)How to Tell Ancient Signs Apart? Recognizing and Visualizing Maya Glyphs with CNNsJournal on Computing and Cultural Heritage 10.1145/323067011:4(1-25)Online publication date: 5-Dec-2018
https://dl.acm.org/doi/10.1145/3230670
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Issue’s Table of Contents