Statistical Feature-Based Craquelure Classification

Crisologo, Irene; Monterola, Christopher; Soriano, Maricor

doi:10.1142/s012918311101683x

Cited by 4 publications

(3 citation statements)

References 14 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This would allow one to compare the relative degree of alignment of natural crack patterns like polygonal terrain [41,42] and the hydraulic channels of heavily fractured rock [39,43], for example. It would also allow one to better measure manufactured patterns such as craquelure [6,15], or custom-designed micro-cracks [8,9].…”

Section: Extension To Other Crack Networkmentioning

confidence: 99%

See 1 more Smart Citation

Crack patterns over uneven substrates

Pawan

Goehring

2016

Soft Matter

View full text Add to dashboard Cite

Cracks in thin layers are influenced by what lies beneath them. From buried craters to crocodile skin, crack patterns are found over an enormous range of length scales. Regardless of absolute size, their substrates can dramatically influence how cracks form, guiding them in some cases, or shielding regions from them in others. Here we investigate how a substrate's shape affects the appearance of cracks above it, by preparing mud cracks over sinusoidally varying surfaces. We find that as the thickness of the cracking layer increases, the observed crack patterns change from wavy to ladder-like to isotropic. Two order parameters are introduced to measure the relative alignment of these crack networks, and, along with Fourier methods, are used to characterise the transitions between crack pattern types. Finally, we explain these results with a model, based on the Griffith criteria of fracture, that identifies the conditions for which straight or wavy cracks will be seen, and predicts how well-ordered the cracks will be. Our metrics and results can be applied to any situation where connected networks of cracks are expected, or found.

show abstract

Section: Extension To Other Crack Networkmentioning

confidence: 99%

“…Such craquelure patterns are extremely hard to forge, and can thus aid in the attribution of paintings [6]. They have been shown to be influenced by local painting style, choice of substrate, including, for paint on wood, even the species of wood used [6,15]. The analysis of similar patterns, in dried blood ( Fig.…”

Section: Introductionmentioning

confidence: 99%

Crack patterns over uneven substrates

Pawan

Goehring

2016

Soft Matter

View full text Add to dashboard Cite

show abstract

“…In addition, such algorithms can be extended to monitor the crack formations on paintings as a way of developing a 'health monitoring system' to be used by art conservators. This paper will extend on the work previously carried out in [3][4][5] to develop a robust algorithm for the geographical and condition-based analysis of artworks using craquelure.…”

Section: Introductionmentioning

confidence: 91%

The development of a diagnostic method for geographical and condition-based analysis of artworks using craquelure pattern recognition techniques

El-Youssef¹,

Bucklow²,

Maev³

2014

Insight

View full text Add to dashboard Cite

The analysis of craquelure found on art paintings has been shown to provide supportive information regarding an art painting's geographical origins and authenticity. Craquelure represents the unique crack formations on paintings that can be traced back to the materials and methods employed by the artist, which is usually confined to the particular geographical area in which the painting was created or stored. It has been shown that different art paintings created in the same geographical location, during a similar time period, exhibit similar craquelure formation patterns. To alleviate expertise in the classification of craquelure patterns to their corresponding region of origin, a computer algorithm has been developed to complete such a task, as well as to monitor the growth and changes in craquelure formations. Mathematical morphology was used to extract the craquelure patterns from a greyscale image before converting it to a binary image. Specific features were then extracted from the binary image and fed to a discriminant analysis classifier for classification. The extracted craquelure network is then saved to a storage database for the purpose of monitoring the painting's crack formation over time. In this report, a set of previously captured craquelure images were used to test the developed algorithm. The results in this paper demonstrate that the computer algorithm is capable of classifying the various craquelure patterns with an acceptable degree of accuracy. It is also shown that the developed algorithm can be used to detect the formation of new cracks as a way of monitoring an art painting's condition. This algorithm has direct applications in the detection of forgeries of art paintings and in the development of a 'health' monitoring system, especially for art paintings that are routinely transported between exhibits.

show abstract

Image Data Mining Based on Wavelet Transform for Visualization of the Unique Characteristics of Image Data

Gebremeskel

Chai

Zhou

et al. 2016

Handbook of Research on Emerging Perspectives in Intelligent Pattern Recognition, Analysis, and Image Processing

View full text Add to dashboard Cite

Mining techniques can play an important role in image decomposition, segmentation, classification and retrieval systems. As image data become more complex and growing at a fast pace, searching valuable information and knowledge implicit become more challenging than ever before. In this chapter, authors proposed a WT based DM techniques to optimize and characterize the unique feature of image retrieval, which is fundamental to optimize informative mathematical representation of image objects. Many software, including data exploratory tools such as DM packages contain fast and efficient programs that perform WT. Wavelets have quickly gained popularity among scientists and engineers, both in theoretical research and in applications. The authors discussed in details and introduced a novel method for image database analysis in different scenarios that foster the wide access of image data.

show abstract

Statistical Feature-Based Craquelure Classification

Cited by 4 publications

References 14 publications

Crack patterns over uneven substrates

Crack patterns over uneven substrates

The development of a diagnostic method for geographical and condition-based analysis of artworks using craquelure pattern recognition techniques

Image Data Mining Based on Wavelet Transform for Visualization of the Unique Characteristics of Image Data

Contact Info

Product

Resources

About