The objective of this work is to recognize object categories in paintings, such as cars, cows and cathedrals. We achieve this by training classifiers from natural images of the objects. We make the following contributions: (i) we measure the extent of the domain shift problem for image-level classifiers trained on natural images vs paintings, for a variety of CNN architectures; (ii) we demonstr...

We examine two paintings by Piet Mondrian, and suggest that his depiction of tree foliages exhibit fractal patterns of a specific dimension. Our analysis implies that fractality may possess an aesthetic value that affected Mondrian, perhaps in a similar way as it inspired Jackson Pollock, another famous painter who incorporated fractality in several of his paintings. In recent years there has b...

This paper describes an automatic approach in archaeological photogrammetry for the documentation and recovery of rupestrian paintings. Visible and near-infrared images were taken from an opened-cave before and after moistening the stone wall. Digital image processing techniques, specially multispectral and multiband classifications, were used to recognise and extract nondestructively the primi...

Statistical analysis of art, particularly of the abstract genre, is becoming an increasingly important tool for understanding the image creation process. We present a multifractal clustering analysis of non-representational images painted by adults and children using a ‘pouring’ technique. The effective dimensions (D0) are measured for each, as is the associated multifractal depth ΔD = D0 D∞. I...

aughty, sharp-tongued, self-assured, unbearably self-sufficient, stingy, and violent beyond measure , " is how Georges de La Tour was described by his contemporaries. Municipal records confirm that he refused to pay his share to feed the hungry during times of famine. He assaulted an officer, beat a peasant, and made himself obnoxious to everyone by " sending his dogs after hare into the standi...

The older paintings suffer from breaks in the substrate, the paint, or the varnish. When we digitized these paintings, they can be modified using mathematical algorithms and cracks are eliminated so as to maintain the quality. The field of computer vision is concerned with extracting features and information from images in order to make analysis of images easier, so that more and more informati...

In this paper, we analyze the fracture patterns observed in wall paintings excavated from Akrotiri, a Bronze-age Aegean city destroyed by earthquakes preceding a volcanic eruption on Thera (modern Santorini) around 1630 BC. We use interactive programs to trace detailed fragment boundaries in images of manually reconstructed wall paintings. Then, we use geometric analysis algorithms to study the...

In this paper, we analyze a sample of clippings from paintings by the late artist Bob Ross. Previous work focused on the qualitative themes of his paintings (Hickey, 2014); here, we expand on that line of research by considering the colorspace and luminosity values as our data. Our results demonstrate the subtle aesthetics of the average Ross painting, the common variation shared by his paintin...