Hybrid Active Contour Model for Segmentation of Synthetic and Real Images

EasyChair Preprint 6759

Abstract

Level set models are extensively used for image segmentation because of their capability to handle topological changes. In this paper, the proposed model uses combined local image information and global image information to evolve the contour around the object boundary, making it robust, irrespective of the inhomogeneity. The proposed model is capable to deal with bias conditions, such as intensity inhomogeneity and light effects. We test this model on synthetic, and real images, confirming its superiority over previous models.

Keyphrases: Local Binary Fitting Energy, Real Image, active contour, active contours, image processing, image segmentation, level set

@booklet{EasyChair:6759,
  author    = {Ehtesham Iqbal and Asim Niaz and Asad Munir and Kwang Nam Choi},
  title     = {Hybrid Active Contour Model for Segmentation of Synthetic and Real Images},
  howpublished = {EasyChair Preprint 6759},
  year      = {EasyChair, 2021}}