Color image segmentation by the vector-valued Allen-Cahn phase-field model: a multigrid solution.

Journal article

We present an efficient numerical solution of a PDE-driven model for color image segmentation and give numerical examples of the results. The method combines the vector-valued Allen-Cahn phase field equation with initial data fitting terms with prescribed interface width and fidelity constants. Efficient numerical solution is achieved using a multigrid splitting of a finite element space, thereby producing an efficient and robust method for the segmentation of large images. We also present the use of adaptive mesh refinement to further speed up the segmentation process.

Authors: Kay, D; Tomasi, A

• Publication status: Published
• Journal: IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
• Volume: 18
• Issue: 10
• Pages: 2330-2339
• Publication date: 2009-10-01
• DOI: 10.1109/tip.2009.2026678
• EISSN: 1941-0042
• ISSN: 1057-7149
• Language: English
• Keywords: Image Enhancement; Color; Reproducibility of Results; Subtraction Technique; Image Interpretation, Computer-Assisted; Algorithms; Sensitivity and Specificity; Artificial Intelligence; Colorimetry; Pattern Recognition, Automated