Fast Image Blending Using Seeded Region Growing

Authors

Yili Zhao, 1. School of Information, Yunnan University, Kunming 650091, China;;2. School of Computer and Information, Southwest Forestry University, Kunming 650224, China;
Xu Dan, 1. School of Information, Yunnan University, Kunming 650091, China;;
Wenhua Qian, 1. School of Information, Yunnan University, Kunming 650091, China;;
Zhang Yan, 2. School of Computer and Information, Southwest Forestry University, Kunming 650224, China;

Abstract

Abstract: This paper presented a novel approach for combining and blending a set of aligned images into a composite mosaic with no visible seams. The compositing seam is found efficiently via seeded region growing using a photometric criterion. A contribution of this paper is to use seeded region growing on image differences to find possible seams over areas of low photometric difference. This can result in significant reduction of blending time. The using of seeded region growing over image pairs guaranteed the approximate optimal solution for each intersection region. The independence of such regions makes the algorithm suitable for parallel implementation. The proposed method is evaluated with pixel based graph cut and watershed based graph cut with qualitative and quantitative comparison.

Recommended Citation

Zhao, Yili; Dan, Xu; Qian, Wenhua; and Yan, Zhang (2020) "Fast Image Blending Using Seeded Region Growing," Journal of System Simulation: Vol. 28: Iss. 9, Article 9.
Available at: https://dc-china-simulation.researchcommons.org/journal/vol28/iss9/9

First Page

1985

Revised Date

2015-07-24

DOI Link

https://doi.org/

Last Page

1989

CLC

TP391.9

Recommended Citation

ZhaoYili, Xu Dan, Qian Wenhua, Zhang Yan. Fast Image Blending Using Seeded Region Growing[J]. Journal of System Simulation, 2016, 28(9): 1985-1989.