Unseeded region growing for 3D image segmentation

Abstract

Unseeded region growing is a versatile and fully automatic segmentation technique suitable for multispectral and 3D images. This approach integrates region-based segmenta- tion with image processing techniques based on adaptive anisotropic diffusion filters. The segmentation method is fast, reliable and free of tun- ing parameters. It is indeed a general purpose segmenta- tion method and has been successfully applied in a range of image analysis tasks. This paper describes the algo- rithm, and briefly discusses its properties and applications. Segmentation results will also be shown at the end of the paper.