Spectral Segmentation with Multiscale Graph Decomposition
Citations Over TimeTop 1% of 2005 papers
Abstract
We present a multiscale spectral image segmentation algorithm. In contrast to most multiscale image processing, this algorithm works on multiple scales of the image in parallel, without iteration, to capture both coarse and fine level details. The algorithm is computationally efficient, allowing to segment large images. We use the normalized cut graph partitioning framework of image segmentation. We construct a graph encoding pairwise pixel affinity, and partition the graph for image segmentation. We demonstrate that large image graphs can be compressed into multiple scales capturing image structure at increasingly large neighborhood. We show that the decomposition of the image segmentation graph into different scales can be determined by ecological statistics on the image grouping cues. Our segmentation algorithm works simultaneously across the graph scales, with an inter-scale constraint to ensure communication and consistency between the segmentations at each scale. As the results show, we incorporate long-range connections with linear-time complexity, providing high-quality segmentations efficiently. Images that previously could not be processed because of their size have been accurately segmented thanks to this method.
Related Papers
- → A study and comparison of different image segmentation algorithms(2016)28 cited
- Image Segmentation Based on Graph Theory Algorithm Simulation Research(2011)
- An Efficient Mean Shift and Graph Based Image Segmentation(2014)
- → Clustering Analysis Based on Segmented Images(2018)
- → An Image Segmentation Algorithm for Fusing Depth Information(2023)