The identification of the artist of a painting is also known as art authentication, and the answer to this question is manifest through art gallery exhibition and is reinforced through financial transactions. Art authentication has visual influence via the uniqueness of the artist’s style in contrast to the style of another artist. The significance of this contrast is proportional to the number of artists involved and the degree of uniqueness of an artist’s collection. This visual uniqueness of style can be captured in a mathematical model produced by a machine learning algorithm on painting images. Art authentication is not always possible since art can be anonymous, forged, gifted, or stolen. Here we show an image only art authentication attribute marker for WikiArt, Rijksmuseum, and ArtFinder galleries. Contributions to the field of art authentication include the identification of a state-of-the-art machine learning algorithm, an extension to this algorithm, standard data sources for art galleries, standard performance measurements, standard combined measurement for accuracy and multi-class cardinality, limits to multi-class cardinality, and application recommendations for the produced models.
