Iterative threshold segmentation method based on information entropy

Jiwen Cui; Dongyu Guo; Zhe Li

doi:10.1117/12.2611613

19 November 2021 Iterative threshold segmentation method based on information entropy

Jiwen Cui, Dongyu Guo, Zhe Li

Proceedings Volume 12059, Tenth International Symposium on Precision Mechanical Measurements; 120590F (2021) https://doi.org/10.1117/12.2611613
Event: Tenth International Symposium on Precision Mechanical Measurements, 2021, Qingdao, China

Abstract

Light strip extraction is important in a structured light measurement system. However, the extraction of light strip is incomplete, losing the information, in the detection of highly reflective surface. This paper presents an iterative threshold segmentation algorithm based on information entropy. Firstly, the image is initially segmented, then using the eightneighborhood detection to remove the noise and retain the light strip, after which the iterative segmentation is carried out with the inflection point of the information entropy of the extracted image as the termination condition to improve the integrity of the light strip segmentation and avoid the excessive segmentation of the background. Compared with the results of Otsu algorithm, the proposed method can retain more complete light strip information, with fewer breaking points.

Citation Download Citation

Jiwen Cui, Dongyu Guo, and Zhe Li "Iterative threshold segmentation method based on information entropy", Proc. SPIE 12059, Tenth International Symposium on Precision Mechanical Measurements, 120590F (19 November 2021); https://doi.org/10.1117/12.2611613

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