Review: Learning how to match fresco fragments

Egon van den Broek

Research output: Contribution to journalBook/Film/Article reviewAcademic

11 Downloads (Pure)

Abstract

This paper was presented at Eurographics 2011. Being among the conference’s best papers, it was revised and republished in this ACM journal. In general, the authors present their approach as new; however, while this is not the case, it is probably an advancement in the domain of cultural heritage. The idea of using patches is well known in the field of image retrieval, although named differently: for example, blobs [1], visual alphabets [2,3], and codebooks [4,5]. Basically, feature selection is presented as a new phase in the image classification processing pipeline, which is a standard phase in machine learning (and, as such, in image classification). A set of features specific to frescos is defined. The actual classification of the fresco’s feature sets is conducted using WEKA’s M5P regression tree [6] and is executed on three datasets. Although not stated explicitly, the readers have to assume the default WEKA settings have been used. The main contribution of this work is the definition of a set of features derived from frescos, which is both a new and promising development for this particular part of our cultural heritage. However, it should be noted that their true value needs to be determined in follow-up validation studies. References 1) Carson, C.; Belongie, S.; Greenspan, H.; Malik, J. Blobworld: image segmentation using expectation-maximization and its application to image querying. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 8(2002), 1026–1038. http://dx.doi.org/10.1109/TPAMI.2002.1023800. 2) Israël, M.; van den Broek, E. L.; van der Putten, P.; den Uyl, M. J. Multimedia data mining and knowledge discovery. Springer-Verlag, 2007, http://dx.doi.org/10.1007/978-1-84628-799-2_10. 3) Israël, M.; van der Schaar, J.; van den Broek, E. L.; den Uyl, M. J.; van der Putten, P. Multi-level visual alphabets. In International Conference on Image Processing Theory, Tools & Applications Djemal, K., Deriche, M., Eds. IEEE Computer Society Press, Piscataway, NJ, 2010, 349–354. http://dx.doi.org/10.1109/IPTA.2010.5586757 4) Carrato, S. Image vector quantization using ordered codebooks: properties and applications. Signal Processing 40, 1(1994), 87–103. http://dx.doi.org/10.1016/0165-1684(94)90023-X. 5) van Gemert, J. C.; Snoek, C. G. M.; Veenman, C. J.; Smeulders, A. W. M.; Geusebroek, J. M. Comparing compact codebooks for visual categorization. Computer Vision and Image Understanding 114, 4(2010), 450–462. http://dx.doi.org10.1016/j.cviu.2009.08.004. 6) Hall, M.; Frank, E.; Holmes, G.; Pfahringer, B.; Reutemann, P.; Witten, I. H. The WEKA data mining software: an update. ACM SIGKDD Explorations Newsletter 11, 1(2009), 10–18. http://www.kdd.org/explorations/issues/11-1-2009-07/p2V11n1.pdf.
Original languageUndefined
Pages (from-to)CR139957
Number of pages1
JournalComputing reviews
Publication statusPublished - 8 Mar 2012

Keywords

  • EWI-21684
  • HMI-MR: MULTIMEDIA RETRIEVAL
  • HMI-VRG: Virtual Reality and Graphics
  • frescos
  • Content-Based Image Retrieval
  • Cultural Heritage
  • Image Processing
  • METIS-286297
  • IR-79948

Cite this

van den Broek, Egon. / Review: Learning how to match fresco fragments. In: Computing reviews. 2012 ; pp. CR139957.
@article{6ceb17bde25c4da49513f8dc2601e7cc,
title = "Review: Learning how to match fresco fragments",
abstract = "This paper was presented at Eurographics 2011. Being among the conference’s best papers, it was revised and republished in this ACM journal. In general, the authors present their approach as new; however, while this is not the case, it is probably an advancement in the domain of cultural heritage. The idea of using patches is well known in the field of image retrieval, although named differently: for example, blobs [1], visual alphabets [2,3], and codebooks [4,5]. Basically, feature selection is presented as a new phase in the image classification processing pipeline, which is a standard phase in machine learning (and, as such, in image classification). A set of features specific to frescos is defined. The actual classification of the fresco’s feature sets is conducted using WEKA’s M5P regression tree [6] and is executed on three datasets. Although not stated explicitly, the readers have to assume the default WEKA settings have been used. The main contribution of this work is the definition of a set of features derived from frescos, which is both a new and promising development for this particular part of our cultural heritage. However, it should be noted that their true value needs to be determined in follow-up validation studies. References 1) Carson, C.; Belongie, S.; Greenspan, H.; Malik, J. Blobworld: image segmentation using expectation-maximization and its application to image querying. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 8(2002), 1026–1038. http://dx.doi.org/10.1109/TPAMI.2002.1023800. 2) Isra{\"e}l, M.; van den Broek, E. L.; van der Putten, P.; den Uyl, M. J. Multimedia data mining and knowledge discovery. Springer-Verlag, 2007, http://dx.doi.org/10.1007/978-1-84628-799-2_10. 3) Isra{\"e}l, M.; van der Schaar, J.; van den Broek, E. L.; den Uyl, M. J.; van der Putten, P. Multi-level visual alphabets. In International Conference on Image Processing Theory, Tools & Applications Djemal, K., Deriche, M., Eds. IEEE Computer Society Press, Piscataway, NJ, 2010, 349–354. http://dx.doi.org/10.1109/IPTA.2010.5586757 4) Carrato, S. Image vector quantization using ordered codebooks: properties and applications. Signal Processing 40, 1(1994), 87–103. http://dx.doi.org/10.1016/0165-1684(94)90023-X. 5) van Gemert, J. C.; Snoek, C. G. M.; Veenman, C. J.; Smeulders, A. W. M.; Geusebroek, J. M. Comparing compact codebooks for visual categorization. Computer Vision and Image Understanding 114, 4(2010), 450–462. http://dx.doi.org10.1016/j.cviu.2009.08.004. 6) Hall, M.; Frank, E.; Holmes, G.; Pfahringer, B.; Reutemann, P.; Witten, I. H. The WEKA data mining software: an update. ACM SIGKDD Explorations Newsletter 11, 1(2009), 10–18. http://www.kdd.org/explorations/issues/11-1-2009-07/p2V11n1.pdf.",
keywords = "EWI-21684, HMI-MR: MULTIMEDIA RETRIEVAL, HMI-VRG: Virtual Reality and Graphics, frescos, Content-Based Image Retrieval, Cultural Heritage, Image Processing, METIS-286297, IR-79948",
author = "{van den Broek}, Egon",
year = "2012",
month = "3",
day = "8",
language = "Undefined",
pages = "CR139957",
journal = "Computing reviews",
issn = "0010-4884",
publisher = "Association for Computing Machinery (ACM)",

}

Review: Learning how to match fresco fragments. / van den Broek, Egon.

In: Computing reviews, 08.03.2012, p. CR139957.

Research output: Contribution to journalBook/Film/Article reviewAcademic

TY - JOUR

T1 - Review: Learning how to match fresco fragments

AU - van den Broek, Egon

PY - 2012/3/8

Y1 - 2012/3/8

N2 - This paper was presented at Eurographics 2011. Being among the conference’s best papers, it was revised and republished in this ACM journal. In general, the authors present their approach as new; however, while this is not the case, it is probably an advancement in the domain of cultural heritage. The idea of using patches is well known in the field of image retrieval, although named differently: for example, blobs [1], visual alphabets [2,3], and codebooks [4,5]. Basically, feature selection is presented as a new phase in the image classification processing pipeline, which is a standard phase in machine learning (and, as such, in image classification). A set of features specific to frescos is defined. The actual classification of the fresco’s feature sets is conducted using WEKA’s M5P regression tree [6] and is executed on three datasets. Although not stated explicitly, the readers have to assume the default WEKA settings have been used. The main contribution of this work is the definition of a set of features derived from frescos, which is both a new and promising development for this particular part of our cultural heritage. However, it should be noted that their true value needs to be determined in follow-up validation studies. References 1) Carson, C.; Belongie, S.; Greenspan, H.; Malik, J. Blobworld: image segmentation using expectation-maximization and its application to image querying. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 8(2002), 1026–1038. http://dx.doi.org/10.1109/TPAMI.2002.1023800. 2) Israël, M.; van den Broek, E. L.; van der Putten, P.; den Uyl, M. J. Multimedia data mining and knowledge discovery. Springer-Verlag, 2007, http://dx.doi.org/10.1007/978-1-84628-799-2_10. 3) Israël, M.; van der Schaar, J.; van den Broek, E. L.; den Uyl, M. J.; van der Putten, P. Multi-level visual alphabets. In International Conference on Image Processing Theory, Tools & Applications Djemal, K., Deriche, M., Eds. IEEE Computer Society Press, Piscataway, NJ, 2010, 349–354. http://dx.doi.org/10.1109/IPTA.2010.5586757 4) Carrato, S. Image vector quantization using ordered codebooks: properties and applications. Signal Processing 40, 1(1994), 87–103. http://dx.doi.org/10.1016/0165-1684(94)90023-X. 5) van Gemert, J. C.; Snoek, C. G. M.; Veenman, C. J.; Smeulders, A. W. M.; Geusebroek, J. M. Comparing compact codebooks for visual categorization. Computer Vision and Image Understanding 114, 4(2010), 450–462. http://dx.doi.org10.1016/j.cviu.2009.08.004. 6) Hall, M.; Frank, E.; Holmes, G.; Pfahringer, B.; Reutemann, P.; Witten, I. H. The WEKA data mining software: an update. ACM SIGKDD Explorations Newsletter 11, 1(2009), 10–18. http://www.kdd.org/explorations/issues/11-1-2009-07/p2V11n1.pdf.

AB - This paper was presented at Eurographics 2011. Being among the conference’s best papers, it was revised and republished in this ACM journal. In general, the authors present their approach as new; however, while this is not the case, it is probably an advancement in the domain of cultural heritage. The idea of using patches is well known in the field of image retrieval, although named differently: for example, blobs [1], visual alphabets [2,3], and codebooks [4,5]. Basically, feature selection is presented as a new phase in the image classification processing pipeline, which is a standard phase in machine learning (and, as such, in image classification). A set of features specific to frescos is defined. The actual classification of the fresco’s feature sets is conducted using WEKA’s M5P regression tree [6] and is executed on three datasets. Although not stated explicitly, the readers have to assume the default WEKA settings have been used. The main contribution of this work is the definition of a set of features derived from frescos, which is both a new and promising development for this particular part of our cultural heritage. However, it should be noted that their true value needs to be determined in follow-up validation studies. References 1) Carson, C.; Belongie, S.; Greenspan, H.; Malik, J. Blobworld: image segmentation using expectation-maximization and its application to image querying. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 8(2002), 1026–1038. http://dx.doi.org/10.1109/TPAMI.2002.1023800. 2) Israël, M.; van den Broek, E. L.; van der Putten, P.; den Uyl, M. J. Multimedia data mining and knowledge discovery. Springer-Verlag, 2007, http://dx.doi.org/10.1007/978-1-84628-799-2_10. 3) Israël, M.; van der Schaar, J.; van den Broek, E. L.; den Uyl, M. J.; van der Putten, P. Multi-level visual alphabets. In International Conference on Image Processing Theory, Tools & Applications Djemal, K., Deriche, M., Eds. IEEE Computer Society Press, Piscataway, NJ, 2010, 349–354. http://dx.doi.org/10.1109/IPTA.2010.5586757 4) Carrato, S. Image vector quantization using ordered codebooks: properties and applications. Signal Processing 40, 1(1994), 87–103. http://dx.doi.org/10.1016/0165-1684(94)90023-X. 5) van Gemert, J. C.; Snoek, C. G. M.; Veenman, C. J.; Smeulders, A. W. M.; Geusebroek, J. M. Comparing compact codebooks for visual categorization. Computer Vision and Image Understanding 114, 4(2010), 450–462. http://dx.doi.org10.1016/j.cviu.2009.08.004. 6) Hall, M.; Frank, E.; Holmes, G.; Pfahringer, B.; Reutemann, P.; Witten, I. H. The WEKA data mining software: an update. ACM SIGKDD Explorations Newsletter 11, 1(2009), 10–18. http://www.kdd.org/explorations/issues/11-1-2009-07/p2V11n1.pdf.

KW - EWI-21684

KW - HMI-MR: MULTIMEDIA RETRIEVAL

KW - HMI-VRG: Virtual Reality and Graphics

KW - frescos

KW - Content-Based Image Retrieval

KW - Cultural Heritage

KW - Image Processing

KW - METIS-286297

KW - IR-79948

M3 - Book/Film/Article review

SP - CR139957

JO - Computing reviews

JF - Computing reviews

SN - 0010-4884

ER -