Image recognition using maximal cliques of interest points

This paper describes a method for extracting interest points in images and using interrelated groups or cliques to recognize structure common to pairs of images. Feature measurements are commonly selected intuitively and work well on data that are thoroughly understood. This approach avoids the use of global features and relies upon candidate interest points and their relationships with each other. The method is applied to photos of movies posters and the results are compared with those achieved with SIFT key points.