Vancouver, BC, Canada
July 7, 2001 to July 14, 2001
Kar-Han Tan , University of Illinois at Urbana-Champaign
Narendra Ahuja , University of Illinois at Urbana-Champaign
We present in this paper the design of an interactive tool for selecting objects using simple freehand sketches. The objective is to extract object boundaries precisely while requiring little skill and time from the user.The tool proposed achieves this objective by integrating user input and image computation in a two-phase algorithm. In the first phase, the input sketch is used along with a coarse global segmentation of the image to derive an initial selection and a triangulation of the region around the boundary. The triangles are used to formulate subproblems of local finer-grained segmentation and selection.Each of the subproblems is processed independently in the second phase,where a linear approximation of the local boundary as well as a local, finer-grained segmentation are computed. The approximate boundary is then used with the local segmentation to compute a final selection, represented with an alpha channel to fully capture diffused object boundaries. Experimental results show that the tool allows very simple sketches to be used to select objects with complex boundaries. Therefore, the tool has immediate applications in graphics systems for image editing, manipulation, synthesis, retrieval, and processing.
Kar-Han Tan, Narendra Ahuja, "Selecting Objects With Freehand Sketches", ICCV, 2001, Proceedings Eighth IEEE International Conference on Computer Vision, Proceedings Eighth IEEE International Conference on Computer Vision 2001, pp. 337, doi:10.1109/ICCV.2001.10024