FLIC: Fast Linear Iterative Clustering with Active Search
This is an incremental improvement for image segmentation, addressing efficiency and accuracy issues in a widely used over-segmentation tool.
The paper tackles the sub-optimal boundary adaptation and slow convergence of Simple Linear Iterative Clustering (SLIC) by proposing FLIC, which uses active search and joint assignment-update steps, achieving approximately 30fps on a 481x321 image with a single CPU core and outperforming competitive methods on the Berkeley segmentation benchmark.
Benefiting from its high efficiency and simplicity, Simple Linear Iterative Clustering (SLIC) remains one of the most popular over-segmentation tools. However, due to explicit enforcement of spatial similarity for region continuity, the boundary adaptation of SLIC is sub-optimal. It also has drawbacks on convergence rate as a result of both the fixed search region and separately doing the assignment step and the update step. In this paper, we propose an alternative approach to fix the inherent limitations of SLIC. In our approach, each pixel actively searches its corresponding segment under the help of its neighboring pixels, which naturally enables region coherence without being harmful to boundary adaptation. We also jointly perform the assignment and update steps, allowing high convergence rate. Extensive evaluations on Berkeley segmentation benchmark verify that our method outperforms competitive methods under various evaluation metrics. It also has the lowest time cost among existing methods (approximately 30fps for a 481x321 image on a single CPU core).