A SIFT-Based Image Fusion Method

Lu, Danxia; Shi, Hongjian

10.1109/ICSP.2018.8652446

2018

2164-5221

978-1-5386-4674-8

PROCEEDINGS OF 2018 14TH IEEE INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING (ICSP)

2018-August

375-378

12-16 Aug. 2018

Beijing, China

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Aimed at the wrong matching appearance when applying Scale Invariant Feature Transform (SIFT) to image fusion. In this paper, we propose to use the SIFT to find the featured points and matched featured points primarily for image fusion. The double Otsu method and average distance threshold segmentation method are used to remove mismatching points and realize an accurate image registration. Finally, we apply the weight average fusion method to blend source images to obtain the final fused image. The results show that the proposed method can automatically realize high precision in fused images and achieve natural image fusion.

component formatting style styling insert

第一 ; 通讯

英语

CPCI-S ; EI

Engineering ; Telecommunications

Engineering, Electrical & Electronic ; Telecommunications

WOS:000466949200076

20191306685022

Image segmentation

Data Processing and Image Processing:723.2

Web of Science

Southern Univ Sci & Technol, Dept Elect & Elect Engn, Shenzhen, Peoples R China

Lu, Danxia,Shi, Hongjian. A SIFT-Based Image Fusion Method[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2018:375-378.