Human body contour extraction method based on improved Canny operator

Nan Li; Kejie Zhang; Yang Wang; Siyu Liu; Jiapeng Li; Chunyan Liu

doi:10.1117/12.3030997

19 July 2024 Human body contour extraction method based on improved Canny operator

Nan Li, Kejie Zhang, Yang Wang, Siyu Liu, Jiapeng Li, Chunyan Liu

Proceedings Volume 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024); 131817Y (2024) https://doi.org/10.1117/12.3030997
Event: Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 2024, Beijing, China

Abstract

Aiming at the problems that the traditional Canny operator can not protect the edge pixels of Gaussian filter, the point interference of non-human contours is obvious, and the fixed high and low threshold is limited, an improved Canny operator is proposed for the extraction of human contours. Firstly, bilateral filtering is used to replace Gauss filtering to protect image edge; The foreground and background are segmented by the ROI region to eliminate the interference from the background; Then Otsu method (algorithm) is used to calculate the adaptive threshold, and finally better results are obtained by fine-tuning the threshold value. Through experiments, the average accuracy of the improved Canny operator reaches 91.15% in the extraction of human contours, which is more accurate than the traditional Canny operator.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Nan Li, Kejie Zhang, Yang Wang, Siyu Liu, Jiapeng Li, and Chunyan Liu "Human body contour extraction method based on improved Canny operator", Proc. SPIE 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 131817Y (19 July 2024); https://doi.org/10.1117/12.3030997

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