, Volume 19, Issue 2, pp 277-283
Date: 09 Jun 2009

Pearling: Stroke segmentation with crusted pearl strings

Rent the article at a discount

Rent now

* Final gross prices may vary according to local VAT.

Get Access


We introduce a novel segmentation technique, called Pearling, for the semi-automatic extraction of idealized models of networks of strokes (variable width curves) in images. These networks may for example represent roads in an aerial photograph, vessels in a medical scan, or strokes in a drawing. The operator seeds the process by selecting representative areas of good (stroke interior) and bad colors. Then, the operator may either provide a rough trace through a particular path in the stroke graph or simply pick a starting point (seed) on a stroke and a direction of growth. Pearling computes in realtime the centerlines of the strokes, the bifurcations, and the thickness function along each stroke, hence producing a purified medial axis transform of a desired portion of the stroke graph. No prior segmentation or thresholding is required. Simple gestures may be used to trim or extend the selection or to add branches. The realtime performance and reliability of Pearling results from a novel disk-sampling approach, which traces the strokes by optimizing the positions and radii of a discrete series of disks (pearls) along the stroke. A continuous model is defined through subdivision. By design, the idealized pearl string model is slightly wider than necessary to ensure that it contains the stroke boundary. A narrower core model that fits inside the stroke is computed simultaneously. The difference between the pearl string and its core contains the boundary of the stroke and may be used to capture, compress, visualize, or analyze the raw image data along the stroke boundary.

The article is published in the original.
Brian Whited is a Ph.D. candidate in computer science at Georgia Tech. His research primarily deals with shape modeling, morphing and image segmentation techniques. He received his M.S. and B.S degrees in computer science also from Georgia Tech in 2005 and 2003, respectively. While a Ph.D. student, he has worked as a research intern at Siemens Corporate Research as well as Walt Disney Feature Animation.
Jaroslaw (Jarek) Rossignac is a Full Professor of Computing at Georgia Tech. His research focuses on the design, representation, simplification, compression, analysis and visualization of highly complex 3D shapes, structures, and animations. Before joining Georgia Tech in 1996 as the Director of the GVU Center, he was Senior Manager and Visualization Strategist at the IBM TJ. Watson Research Center. He holds a Ph.D. in E.E. from the University of Rochester, a Diplôme d’lngénieur from the Ecole Nationale Supérieure en Électricité et Mécanique (ENSEM), and a Maîtrise in M.E. from the University of Nancy, France. He authored 21 patents and over 110 peer-reviewed articles for which he received 23 Awards. He created the ACM Solid Modeling Symposia and expanded them into the annual Solid and Physical Modeling (SPM) conferences; chaired 25 conferences and program committees; delivered ahout 30 Distinguished or Invited Lectures and Keynotes; and served an the Editorial Boards of 7 professional journals and on 62 Technical Program committees. Currently he heads the NSF Aquatic Propulsion Lab (APL) and the Modeling, Animation, Graphic, Interaction, and Compression (MAGIC) Lab at Georgia Tech, which, among other topics hosts the Disney-sponsored Feature Animation Production Automation (FAPA) project. Rossignac is a Fellow of the Eurographics Association.
Tong Fang received the Ph.D. degree in industrial engineering in 2000 and the M.Sc degrees in electrical and computer engineering in 1999, industrial engineering in 1997 from Rutgers University, New Jersey. In 1992, he received the M.Sc degree in management science from University of Science and Technology, China. He is currently a research scientist and Manger of adaptive techniques R&D program at Siemens Corporate Research, Princeton, New Jersey. His current research interests include geometric modeling and visualization and image processing.
Gregory G. Slabaugh is the Head of Research and Development at Medicsight PLC, an industry leader in the development of computer-aided detection (CAD) software. Greg earned a PhD in Electrical Engineering from the Georgia Institute of Technology in Atlanta, GA, and also held positions at Hewlett-Packard Laboratories in Palo Alto, CA and Siemens Corporate Research in Princeton, NJ. Greg is a Senior Member of IEEE and an Associate Editor of IEEE Signal Processing Magazine. Greg has over 40 publications and over 30 patents pending in the fields of computer vision and medical image processing; in particular, his research interests include computer-ftjt aided detection, image segmentation, registration, computational geometry, multi-view stereo, adaptive filtering, and partial differential equations.
Gozde Unal received the Ph.D. degree in electrical and computer engineering from North Carolina State University, Raleigh, NC, USA in August 2002. Later she was as a postdoctoral fellow at the Georgia Institute of Technology and visited HP Labs, Palo Alto, California, as a postdoctoral researcher during the summer of 2003. From Fall 2003 to 2007, she worked as a research scientist at Siemens Corporate Research, Princeton, NJ USA. She joined the faculty of Sabanci, University, Istanbul, Turkey in Fall 2007, where she is currently an assistant professor. Her current research is focused on medical image analysis, segmentation, registration, and shape analysis techniques with applications to cynically relevant problems in MR, CT, US, and intravascular images. She is a Senior Member of the IEEE, and Associate Editor for IEEE Transactions on Information Technology on Biomedicine.