English

Level Set KSVD

Computer Vision and Pattern Recognition 2023-11-15 v1 Image and Video Processing

Abstract

We present a new algorithm for image segmentation - Level-set KSVD. Level-set KSVD merges the methods of sparse dictionary learning for feature extraction and variational level-set method for image segmentation. Specifically, we use a generalization of the Chan-Vese functional with features learned by KSVD. The motivation for this model is agriculture based. Aerial images are taken in order to detect the spread of fungi in various crops. Our model is tested on such images of cotton fields. The results are compared to other methods.

Keywords

Cite

@article{arxiv.2311.08284,
  title  = {Level Set KSVD},
  author = {Omer Sapir and Iftach Klapp and Nir Sochen},
  journal= {arXiv preprint arXiv:2311.08284},
  year   = {2023}
}

Comments

25 pages, 14 figures. Submitted to IJCV

R2 v1 2026-06-28T13:20:55.075Z