/Puck

Find significant areas in digital images and save them by using the extensible Characterization Language (XCL).

Primary LanguageC++MIT LicenseMIT

Puck

Developed for the Planets Project to find significant areas in digital images and save them by using the extensible Characterization Language (XCL).

The approach is described in the paper Guttenbrunner, Rauber, Thaller, Wieners (2010): "Same Same But Different – Comparing RenderingEnvironments for Interactive Digital Objects".

Puck uses the segmentation algorithm described in the paper Felzenszwalb and Huttenlocher(2004): Efficient Graph-Based Image Segmentation; you can find the source code at http://cs.brown.edu/~pff/segment/.