Computer vision helps observers understand how iconic artworks were created

Paintings are often made up of thousands of tiny brushstrokes, each going in a certain direction, that are not easily observed by the viewer. A cross-disciplinary research team from the Penn State College of Information Sciences and Technology (IST) and Loughborough University in England has developed an image analysis method that helps to make the underlying brushstroke structure of paintings visible, giving new insight into how artists physically created their works.

This approach offers both experts and non-experts a fresh way to observe and interpret the making of artworks. The research was recently published in the journal Patterns.

The researchers bridged art and data science to show that painting style can be quantified and visualized as flow, turning elusive qualities like "gesture" into measurable, analyzable data. They used a computational technique to examine very small patches of Impressionist paintings, determining the direction of the brushstroke in each tiny spot and connect these different directions, as if drawing lines that follow the flow.

This resulted in a set of "streamlines" that trace how the artist's hand and brush moved across the canvas. The study also measured features of the brushstroke flows—length, curvature, direction—so that different artists' styles could be compared.

"This work demonstrates how computer vision and data science can reveal subtle structural patterns in paintings that are difficult for the human eye to detect directly," said co-corresponding author James Wang, distinguished professor in the College of IST's Department of Informatics and Intelligent Systems. "Our method transforms hidden brushstroke information into a visual representation that supports deeper analysis of artistic technique and style."

The streamline visualizations offer a new lens for viewing and interpreting art, according to co-corresponding author Kathryn Brown, reader in art history and digital heritage at Loughborough University.

"They help observers—whether experts or general viewers—better understand how the artist moved their brush, how the painting is organized and how artists' styles differ," Brown said. "Essentially, we have a new computational 'roadmap' for interpreting the development of a painting."

In addition to Wang and Brown, contributors to this research included Lizhen Zhu, a graduating doctoral candidate in informatics advised by Wang, and Chaewan Chun, also a Penn State doctoral candidate in informatics.

This image shows the streamlines extracted from Claude Monet's Haystacks series. The researchers measured the brushstroke patterns in Monet's Haystacks paintings to show how the direction of the brushstrokes reveals both the shape of the haystacks and how light falls on them.

The strokes curve with the form of the haystacks and change depending on lighting, spreading outward in bright light and becoming more parallel in shadow. According to the researchers, this offers new insight into the relationship between Monet's brushwork, his repeated experimentation with a central motif and the rendering of different atmospheric conditions.

• (Center) Original oil-on-canvas paintings
• (Surrounding panels) Colored streamlines over grayscale renderings of the same works
• (A) "Stacks, End of Summer," 1891, Musee d'Orsay, Paris
• (B) "Stacks of Wheat (End of Summer)," 1890-1891, Art Institute of Chicago, Chicago
• (C) "Grainstacks in the Sunlight, Morning Effect," 1890, private collection
• (D) "Wheatstacks, Snow Effect, Morning," 1891, The J. Paul Getty Museum, Los Angeles
• (E) "Grainstack, White Frost Effect," 1890-91, Shelburne Museum, Shelburne, Vermont
• (F) "Grainstack in the Sunlight," 1891, private collection
• (G) "Grainstack. (Sunset.)," 1890-91, Museum of Fine Arts, Boston

This image represents the qualitative visualization and quantitative comparison of streamlines in Impressionist paintings. The researchers measured brushstroke flow—length of lines, curvature, the direction they go, how consistent they are—to compare how different artists' brushwork shapes the feeling and structure of their paintings.

For example, in Renoir's "La Grenouillère," the brushstroke lines are more curved and change direction, reflecting his short, swirling strokes and a more fragmented look. In Monet's version of the same scene, the lines are more consistent and horizontal, showing a more structured style.

A similar contrast appears between Manet's "Nana"—where brushstrokes are more uniform and create a strong sense of structure—and Morisot's "Woman at Her Toilette," where brushstrokes vary widely, making the scene feel more fluid and less defined.

• (A and B) Streamline detection results on Monet's "La Grenouillère" (A) and Renoir's "La Grenouillère" (B)
• (C) "La Grenouillère," Claude Monet, 1869, oil on canvas, Metropolitan Museum of Art, New York
• (D) "La Grenouillère," Pierre-Auguste Renoir, 1869, oil on canvas, Nationalmuseum, Stockholm
• (E–G) Comparative distributions of curvature (E), per-streamline orientation consistency (F), and mean orientation (G) for the works in (A) and (B)
• (H and I) Streamline detection results on Édouard Manet's "Nana" (H) and Berthe Morisot's "Woman at Her Toilette" (I)
• (J) "Nana," Édouard Manet, 1877, oil on canvas, Hamburger Kunsthalle, Germany (K) "Woman at Her Toilette," Berthe Morisot, 1870–1880, oil on canvas, Art Institute of Chicago, Chicago
• (L–N) Comparative distributions of curvature (L), per-streamline orientation consistency (M), and mean orientation (N) for the works in (H) and (I)

This image shows how streamlines extracted from diverse artworks illustrate directional flow across styles. The researchers recorded many tiny details about brushstrokes and turned them into clear, continuous visual maps of how a painting is made. In these paintings, different colors represent different directions, revealing how the brushstrokes move. These visualizations help reveal hidden patterns in brushwork to provide a nuanced way to compare artists and styles.

• (A) "The Scream," Edvard Munch, 1893, tempera and crayon on unprimed cardboard, ProtoExpressionism, Munch Museum, Oslo, Norway
• (B) "Portrait of Madame Matisse. The Green Line," Henri Matisse, 1905, oil on canvas, Fauvism, Statens Museum for Kunst, Copenhagen, Denmark
• (C) "Malle Babbe, Frans Hals," 1633–1635, oil on canvas, Dutch Golden Age, Gemäldegallerie, Berlin, Germany

Provided by Pennsylvania State University