Skip to content

Latest commit

 

History

History
21 lines (12 loc) · 1.25 KB

README.md

File metadata and controls

21 lines (12 loc) · 1.25 KB

Active Contour Without Edges on Wavelet Features

This is a simple implementation of my paper:

Chen, Junyu, et al. "Feature-Based Image Clustering and Segmentation Using Wavelets." arXiv preprint arXiv:1907.03591, 2019.

This method builds on the Active Contour Without Edges (ACWE) to incorporate Wavelet features, with a tunable parameter 'q' to allow to us control the type of information (low-frequency or high-frequency info.) we want to segment.

Data required to run the MATLAB program can be found here: required data.

Sample results for SPECT bone and bone lesion segmentation:

q = 0.75 (Bone Segmentation):

q = 1.7 (Lesion Segmentation):