Lie Detectors for Paintings

Imagine if art historians could determine the authenticity of a work by asking a painting whether it was real or fake? While paintings can’t answer directly, two new techniques for discovering forgeries act as “lie detectors” for works of art.

The first, developed by a team of researchers at Dartmouth, uses a tool in neuroscience research to distinguish fake from genuine :

By using sparse coding technology to mathematically analyze and compare drawings by famed Flemish artist Pieter Bruegel with a known set of imitations, the researchers were able to distinguish between the genuine works and the forgeries.

Sparse coding technology was developed to emulate the human visual system. To translate the complex images first detected by eyes to the simpler models found in the brain, our visual system uses a number of “filter” neurons. These neurons are triggered by specific patterns in the image. The brain has evolved to efficiently identify many predictable patterns found throughout the natural world and is consequently able to minimize the number of filters required per natural image. Conversely, the brain requires many more filters to model images that it has not been previously exposed to.

Hughes, Graham, and Rockmore applied these ideas to their own art authentication technology. Essentially, they imagined a visual system that had evolved while being exposed only to Bruegel drawings. Thus, it would process Bruegel drawings using few filters but would have to use many more when looking at anything else—including Bruegel forgeries.

To create this model the researchers obtained a number of genuine and fake Bruegel drawings. They digitally broke the authentic works up into smaller pieces and using sparse coding technology identified the smallest or “sparsest” set of those pieces that could be used as filters. This set of filters essentially quantified Bruegel’s unique artistic style by capturing properties repeated throughout the artist’s works.

The researchers then used these filters to analyze the collection of both genuine and fake Bruegel works. As they expected, the authentic paintings could be represented with far fewer filters than the imitations required. The difference in the number of filters used by the sparse coding technology allowed the researchers to distinguish between the two.

The second technique, created by Polish scientists, uses medical imaging technology to detect the forgery of an artist’s signature and changes in paintings hundreds of years old:

Associate Professor Piotr Targowski of Nicolaus Copernicus University in Torun, Poland, said easel paintings prepared according to traditional techniques consist of multiple layers. The artist, for instance, first applies a glue sizing over the canvas to ensure proper adhesion of later layers. Those layers may include an outline of the painting, the painting itself, layers of semitransparent glazes, and finally transparent varnish.

Although a variety of technologies is used to detect forgeries or alterations of such works of art, some of the technologies might damage the paintings or not be sensitive enough to detect finer details.

In the new study, the scientists utilized a medical technique called Optical Coherence Tomography that is used to produce three-dimensional images of the layers of the retina.

They said they used OCT to analyze two oil paintings from the 18th and 19th centuries. In one, “Saint Leonard of Porto Maurizio,” OCT revealed evidence that the inscription “St. Leonard” was added approximately fifty years after completion of the painting. In the other, “Portrait of an unknown woman,” OCT found evidence of the possible forgery of the artist’s signature.

(Via: i09 )