English

A novel automatic thresholding segmentation method with local adaptive thresholds

Computer Vision and Pattern Recognition 2013-05-23 v1

Abstract

A novel method for segmenting bright objects from dark background for grayscale image is proposed. The concept of this method can be stated simply as: to pick out the local-thinnest bands on the grayscale grade-map. It turns out to be a threshold-based method with local adaptive thresholds, where each local threshold is determined by requiring the average normal-direction gradient on the object boundary to be local minimal. The method is highly automatic and the segmentation mimics a man's natural expectation even the object boundaries are fuzzy.

Keywords

Cite

@article{arxiv.1305.5160,
  title  = {A novel automatic thresholding segmentation method with local adaptive thresholds},
  author = {Bo Xiao and Yuefeng Jing and Yonghong Guan},
  journal= {arXiv preprint arXiv:1305.5160},
  year   = {2013}
}

Comments

3 pages, 6 figures

R2 v1 2026-06-22T00:20:33.358Z