A digital technique for art authentication

By Siwei Lyu, D. Rockmore, Hany Farid. 2004

211 citations recorded by the source corpus.

We describe a computational technique for authenticating works of art, specifically paintings and drawings, from high-resolution digital scans of the original works. This approach builds a statistical model of an artist from the scans of a set of authenticated works against which new works then are compared. The statistical model consists of first- and higher-order wavelet statistics. We show preliminary results from our analysis of 13 drawings that at various times have been attributed to Pieter Bruegel the Elder; these results confirm expert authentications. We also apply these techniques to the problem of determining the number of artists that may have contributed to a painting attributed to Pietro Perugino and again achieve an analysis agreeing with expert opinion.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

Recognizing Image Style (2013, background): “We hypothesize that image style may be related to many different features, including low-level statistics [19], color choices, composition, and content.”
Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature (2015, unknown): “(e.g. [25, 18, 22, 15, 6, 19]).”
Behavioural biometrics: a survey and classification (2008, methodology): “Lyu et al. (2004) developed a technique for performing multi-scale, multi-orientation painting scan decomposition.”
Task-Driven Dictionary Learning (2010, methodology): “Recognizing authentic paintings from imitations using statistical techniques has been the topic of a few recent works [52], [53], [54].”
The Rijksmuseum Challenge: Museum-Centered Visual Recognition (2014, background): “Furthermore, wavelet analysis of brush strokes in paintings can reveal artist identity [7, 10], and help in painter authentication [11] Datasets for evaluation automatic analysis of artistic content are typically dedicated to a single art type, not openly available due to copyright constraints and…”
Image processing for artist identification (2008, background): “A survey of the literature [3], [17], [19], [22], [26], [30] reveals that image processing tools aimed at supplementing the art historian’s toolbox are currently in the earliest stages of development.”
Using Color Compatibility for Assessing Image Realism (2007, background): “Farid and colleagues have done extensive work on using higher-order image statistics for a variety of tasks, including distinguishing between computer renderings and photographs [12], detecting digital tampering, finding art fakes [13], etc.”
Image retrieval: Ideas, influences, and trends of the new age (2008, methodology): “Statistical methods can sometime capture subtle characteristics of art which even a human eye can miss [Lyu et al. 2004].”