Volume 6, Issue 1
Integrating Feature Direction Information with a Level

Meng Li & Yi Zhan

East Asian J. Appl. Math., 6 (2016), pp. 1-22.

Published online: 2018-02

Preview Full PDF 716 3406
Export citation
  • Abstract

A feature-dependent variational level set formulation is proposed for image segmentation. Two second order directional derivatives act as the external constraint in the level set evolution, with the directional derivative across the image features direction playing a key role in contour extraction and another only slightly contributes. To overcome the local gradient limit, we integrate the information from the maximal (in magnitude) second-order directional derivative into a common variational framework. It naturally encourages the level set function to deform (up or down) in opposite directions on either side of the image edges, and thus automatically generates object contours. An additional benefit of this proposed model is that it does not require manual initial contours, and ourmethod can capture weak objects in noisy or intensity-inhomogeneous images. Experiments on infrared and medical images demonstrate its advantages.

  • Keywords

Image segmentation, level set evolution, variational model, image feature, maximal second-order directional derivative.

  • AMS Subject Headings

65M10, 78A48

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{EAJAM-6-1, author = {}, title = {Integrating Feature Direction Information with a Level}, journal = {East Asian Journal on Applied Mathematics}, year = {2018}, volume = {6}, number = {1}, pages = {1--22}, abstract = {

A feature-dependent variational level set formulation is proposed for image segmentation. Two second order directional derivatives act as the external constraint in the level set evolution, with the directional derivative across the image features direction playing a key role in contour extraction and another only slightly contributes. To overcome the local gradient limit, we integrate the information from the maximal (in magnitude) second-order directional derivative into a common variational framework. It naturally encourages the level set function to deform (up or down) in opposite directions on either side of the image edges, and thus automatically generates object contours. An additional benefit of this proposed model is that it does not require manual initial contours, and ourmethod can capture weak objects in noisy or intensity-inhomogeneous images. Experiments on infrared and medical images demonstrate its advantages.

}, issn = {2079-7370}, doi = {https://doi.org/10.4208/eajam.231114.240915a}, url = {http://global-sci.org/intro/article_detail/eajam/10770.html} }
TY - JOUR T1 - Integrating Feature Direction Information with a Level JO - East Asian Journal on Applied Mathematics VL - 1 SP - 1 EP - 22 PY - 2018 DA - 2018/02 SN - 6 DO - http://doi.org/10.4208/eajam.231114.240915a UR - https://global-sci.org/intro/article_detail/eajam/10770.html KW - Image segmentation, level set evolution, variational model, image feature, maximal second-order directional derivative. AB -

A feature-dependent variational level set formulation is proposed for image segmentation. Two second order directional derivatives act as the external constraint in the level set evolution, with the directional derivative across the image features direction playing a key role in contour extraction and another only slightly contributes. To overcome the local gradient limit, we integrate the information from the maximal (in magnitude) second-order directional derivative into a common variational framework. It naturally encourages the level set function to deform (up or down) in opposite directions on either side of the image edges, and thus automatically generates object contours. An additional benefit of this proposed model is that it does not require manual initial contours, and ourmethod can capture weak objects in noisy or intensity-inhomogeneous images. Experiments on infrared and medical images demonstrate its advantages.

Meng Li & Yi Zhan. (2020). Integrating Feature Direction Information with a Level. East Asian Journal on Applied Mathematics. 6 (1). 1-22. doi:10.4208/eajam.231114.240915a
Copy to clipboard
The citation has been copied to your clipboard