Computer-Aided Interactive Object Delineation Using an Intelligent Paintbrush Technique

A method for fast generic object segmentation is presented that allows the user to quickly paint the object of interest in the image using an intelligent paintbrush. This intelligence is based on a partitioning of the image in segmentation primitives, which are computed automatically by merging watershed regions with similar image intensity distribution using the Minimum Description Length principle. We show results for Magnetic Resonance images of the heart and of the brain and for Computerized Tomography images of the abdomen.

[1]  Luc Vincent,et al.  Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Yvan G. Leclerc,et al.  Constructing simple stable descriptions for image partitioning , 1989, International Journal of Computer Vision.

[3]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[5]  Glynn P. Robinson,et al.  Scale and segmentation of grey-level images using maximum gradient paths , 1991, Image Vis. Comput..

[6]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[7]  David H. Eberly,et al.  Interacting with image hierarchies for fast and accurate object segmentation , 1994, Medical Imaging.

[8]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[9]  Stephen M. Pizer,et al.  Ridge flow models for image segmentation , 1994, Medical Imaging.