Details

Autor(en) / Beteiligte

• Ruiying, He

Titel

Fast extended active contours model without edges

Ist Teil von

• 2021 2nd International Conference on Artificial Intelligence and Information Systems, 2021, p.1-6

Ort / Verlag

New York, NY, USA: ACM

Erscheinungsjahr

2021

Link zum Volltext

Quelle

ACM Digital Library

Beschreibungen/Notizen

• The traditional active contours model without edges (CV model) can not deal with the image with intensity inhomogeneity. Extended active contours model without edges (ECV model) can solve the problem by utilizing image edge information. However, the ECV model still has the disadvantages of slow evolution speed and poor noise resistance. This paper simplifies the ECV model and changes the driving force by simplifying partial differential equation into ordinary differential equation. The experimental results show that the new model is not sensitive to the initial contour of the evolution curve, and can segment the images that can be segmented by ECV model faster, and the robustness to noise is stronger than that of ECV model.