Title :
Image stitching using simplified SIFT
Author :
Zhu Qidan ; Li Ke
Author_Institution :
Autom. Coll., Harbin Eng. Univ., Harbin, China
Abstract :
This paper used the improved simplified SIFT feature to image stitching. In order to enhance the robustness, the gradient direction histogram was smoothed using Gaussian filter. The matching method was also improved to eliminate the error matching and many-to-one match. When computing transformation matrix, we used RANSAC algorithm to improve computational accuracy. Finally, two pictures were integrated by the method of fading out. The experimental results show that this method greatly improved the efficiency of splicing.
Keywords :
Gaussian processes; filtering theory; gradient methods; image processing; iterative methods; matrix algebra; Gaussian filter; RANSAC algorithm; gradient direction histogram; image stitching; simplified SIFT; splicing efficiency; transformation matrix; Automation; Educational institutions; Fading; Filters; Histograms; Image matching; Noise robustness; Smoothing methods; Splicing; Virtual reality; Image Stitching; Improved Matching Algorithm; RANSAC; Simplified SIFT Feature;
Conference_Titel :
Information and Automation (ICIA), 2010 IEEE International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4244-5701-4
DOI :
10.1109/ICINFA.2010.5512313