Variable window and variant threshold segmentation algorithm based on light field intensity

Ji-wen Cui; Jiu-bin Tan; Wen-jing Kang; Lei Ao

doi:10.1117/12.667954

20 January 2006 Variable window and variant threshold segmentation algorithm based on light field intensity

Ji-wen Cui, Jiu-bin Tan, Wen-jing Kang, Lei Ao

Proceedings Volume 6027, ICO20: Optical Information Processing; 60271F (2006) https://doi.org/10.1117/12.667954
Event: ICO20:Optical Devices and Instruments, 2005, Changchun, China

Abstract

Image segmentation is a basic and key technology in image analysis and application. In order to avoid inaccurate segmentation non-homogeneous intensity in light field, a novel segmentation algorithm using variant threshold in variable window is proposed in this paper. In the algorithm, a special window for every point is selected according to special algorithm, and the grayscale of every point in the window is continued to the whole image. In the process of continuation, different weight is allocated to different point according to the weight function in the window by grayscale extremum's sum and difference. So, the grayscale of every point is monotonic in the special window, the variant threshold can be obtained in the selected window for its intensity in light filed, and the segmentation result can be acceptable. The experiment shows that the proposed segmentation algorithm can be used to correctly segment the image with non-homogeneous intensity in light field.

Citation Download Citation

Ji-wen Cui, Jiu-bin Tan, Wen-jing Kang, and Lei Ao "Variable window and variant threshold segmentation algorithm based on light field intensity", Proc. SPIE 6027, ICO20: Optical Information Processing, 60271F (20 January 2006); https://doi.org/10.1117/12.667954

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