אירועים והרצאות בפקולטה למדעי המחשב ע"ש הנרי ומרילין טאוב

Standard image classification algorithms classify an image by its content. Sometimes, we don't care about the image content and want to classify images by style. For example, if we have a set of paintings and we want to divide them to groups by their painting style or painter, we don't care if a car or a horse was painted. Another usage for classifying by style is when we have a painting and we are not sure whether it was really painted by a specific painter, and we want to check whether its style matches the painter's style. We call this image classification problem recognition by graphical style. A related problem is applying an image style to an image. An algorithm that can do that can repaint an image using a specific painter style as if the painter painted this image. The idea is to extract the style of an image (or images) and recreate a different image so it would still have the original image's content but with the extracted image style. We call this problem graphical style synthesis. Both these problems require local analysis of the images instead of global analysis that is done when we look for the image content instead of the image style. We study these problems and develop machine learning based algorithm for recognition by graphical style and heuristic algorithms for graphical style synthesis.