Unsupervised multiscale color image segmentation based on MDL principle
2006
We present an unsupervised multiscale color image segmentation algorithm. The basic idea is to apply mean shift clustering to obtain an over-segmentation and then merge regions at multiple scales to minimize the minimum description length criterion. The performance on the Berkeley segmentation benchmark compares favorably with some existing approaches
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
16
References
56
Citations
NaN
KQI