CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 12803 > Article
Paper
16 October 2023 Research on foreground subject segmentation algorithm with high similarity of foreground background
Yating Shen, Lujie Zeng, Ping Zong
Author Affiliations +
Proceedings Volume 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023); 128030W (2023) https://doi.org/10.1117/12.3009537
Event: 2023 5th International Conference on Artificial Intelligence and Computer Science (AICS 2023), 2023, Wuhan, China
Abstract
One of the advanced algorithms for image foreground segmentation is DIM (Deep Image Matting), which applies convolutional neural networks. However, for complex foreground shapes, fixed convolutional kernels are not the optimal approach. Therefore, Deformable Convolution Networks (DCN) were introduced as a replacement, which partially address the issue of losing edge details in deep layers. However, DCN suffers from the extraction of undesired features, significantly reducing the model’s flexibility. To address this, the bias is reshaped using a balanced refining bias with an adaptive weight matrix, instead of a fixed 9-grid bias. To evaluate the effectiveness of the bias, a simple model called DIM_RDC is designed and trained, which utilizes the balanced refining bias. The model is tested on the Adobe dataset, and the results show that DIM_RDC improves the evaluation metrics of SAD by 1.62% and MSE by 11.05% compared to DIM. Therefore, DIM_RDC demonstrates a certain level of competitiveness over DIM.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Yating Shen, Lujie Zeng, and Ping Zong "Research on foreground subject segmentation algorithm with high similarity of foreground background", Proc. SPIE 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023), 128030W (16 October 2023); https://doi.org/10.1117/12.3009537
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
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
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 7 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation
Image processing algorithms and systems
Education and training
Convolution
Deformation
Data modeling
Feature extraction
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top