Image seam line method based on the combination of dijkstra algorithm and morphology

Daizhi Kuang; Qiming Yan; Yunju Nie; Shengfeng Feng; Jiancheng Li

doi:10.1117/12.2203544

3 December 2015 Image seam line method based on the combination of dijkstra algorithm and morphology

Daizhi Kuang, Qiming Yan, Yunju Nie, Shengfeng Feng, Jiancheng Li

Proceedings Volume 9794, Sixth International Conference on Electronics and Information Engineering; 97941R (2015) https://doi.org/10.1117/12.2203544
Event: Sixth International Conference on Electronics and Information Engineering, 2015, Dalian, China

Abstract

This paper proposes a method of image seam line based on the combination of Dijkstra algorithm and morphology. First, the method determines the differential images of the overlap part of two images. And then, morphological expansion processing is implemented based on the differential images and the eight-neighborhood sparse matrix is constructed according to the sparse matrix. Finally, the seam line with the optimal path can be obtained by automatic search of seam line on the differential images by Dijkstra algorithm. The experimental results show that compared to the Dijkstra method that is not subject to morphological processing, the improved algorithm can avoid the high brightness area as housing under the circumstance of less time (3.72s) in the process of automatic research seam line.

Citation Download Citation

Daizhi Kuang, Qiming Yan, Yunju Nie, Shengfeng Feng, and Jiancheng Li "Image seam line method based on the combination of dijkstra algorithm and morphology", Proc. SPIE 9794, Sixth International Conference on Electronics and Information Engineering, 97941R (3 December 2015); https://doi.org/10.1117/12.2203544

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available