1. Hierarchical image segmentation via recursive superpixel with adaptive regularity
- Author
-
Kensuke Nakamura and Byung-Woo Hong
- Subjects
Pixel ,business.industry ,media_common.quotation_subject ,Fidelity ,Scale-space segmentation ,020206 networking & telecommunications ,Pattern recognition ,02 engineering and technology ,Image segmentation ,Energy minimization ,Residual ,Regularization (mathematics) ,Atomic and Molecular Physics, and Optics ,Computer Science Applications ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Segmentation ,Artificial intelligence ,Electrical and Electronic Engineering ,business ,Mathematics ,media_common - Abstract
A fast and accurate segmentation algorithm in a hierarchical way based on a recursive superpixel technique is presented. We propose a superpixel energy formulation in which the trade-off between data fidelity and regularization is dynamically determined based on the local residual in the energy optimization procedure. We also present an energy optimization algorithm that allows a pixel to be shared by multiple regions to improve the accuracy and appropriate the number of segments. The qualitative and quantitative evaluations demonstrate that our algorithm, combining the proposed energy and optimization, outperforms the conventional k -means algorithm by up to 29.10% in F -measure. We also perform comparative analysis with state-of-the-art algorithms in the hierarchical segmentation. Our algorithm yields smooth regions throughout the hierarchy as opposed to the others that include insignificant details. Our algorithm overtakes the other algorithms in terms of balance between accuracy and computational time. Specifically, our method runs 36.48% faster than the region-merging approach, which is the fastest of the comparing algorithms, while achieving a comparable accuracy.
- Published
- 2017