The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
The image blending method for face swapping
Abstract
Recently, image synthesis technology such as face swapping have been receiving attention gradually. In this issue, the rigid boundary line which is occurred by the large difference of color and brightness between reference and target image in synthesized image is a serious problem. This boundary line is the main cause of unnatural face swapping. In this paper, we propose a blending method which can deal with this problem by adaptive weight value and require low-cost for computation. In experiment, we verify that proposed method can remove the boundary line effectively during the image synthesis and preserve the principal parts of human face such as eyes, nose and mouth. Furthermore, we demonstrate that our method can compute the algorithm with 600 by 600 resolution image in near realtime.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Robust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097
Reinhard, E., Adhikhmin, M., Gooch, B., & Shirley, P. (2001) · IEEE Computer Graphics and Applications · doi:10.1109/38.946629 · Cited by 2,937 · cited 1×
“In this paper we adopt color transfer proposed by E Reinhard et al [2].”
MethodPérez, P., Gangnet, M., & Blake, A. (2003) · ACM SIGGRAPH 2003 Papers · doi:10.1145/1201775.882269 · Cited by 2,020 · cited 1×
“However, many blending methods such as seamless cloning, that proposed by Patrick Perez et al [4], require too many computation although it have a good performance.”
MethodPorter, T., & Duff, T. (1984) · Proceedings of the 11th annual conference on Computer graphics and interactive techniques · doi:10.1145/800031.808606 · Cited by 1,164 · cited 2×
“The alpha blending method, proposed by Thomas Porterd and Tom Duff [3], is to mix two pixel-values derived from synthesis regions of target image and reference image by a certain ratio.”
MethodRobust real-time face detection
Viola, P., & Jones, M. (2005) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937709 · Cited by 898
Porter, T., & Duff, T. (1984) · ACM SIGGRAPH Computer Graphics · doi:10.1145/964965.808606 · Cited by 727
Cited by
DeepFakes: a New Threat to Face Recognition? Assessment and Detection
Korshunov, P., & Marcel, S. (2018) · arXiv · doi:10.48550/arxiv.1812.08685 · Cited by 497
“Until the latest era of neural networks, most of the techniques for face swapping or facial reenacment were based on similarity searchers between faces or face patches in target and source video and various blending techniques [15], [16], [17], [18], [4].”
BackgroundVulnerability assessment and detection of Deepfake videos
Korshunov, P., & Marcel, S. (2019) · 2019 International Conference on Biometrics (ICB) · doi:10.1109/icb45273.2019.8987375 · Cited by 162
“Until the latest era of neural networks, most of the techniques for face swapping or facial reenacment were based on similarity searchers between faces or face patches in target and source video and various blending techniques [3, 23, 6, 13, 15].”
BackgroundPreventing DeepFake Attacks on Speaker Authentication by Dynamic Lip Movement Analysis
Yang, C.-Z., Ma, J., Wang, S., & Liew, A. W. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3045937 · Cited by 119
“…[41]; ii) Synthesize the face of subject two, based on the original face of subject one using an autoencoder network [25] or a Generative Adversarial Network (GAN) [26]; iii) Insert the synthesized face into the original image/video with some kind of blending postprocessing steps [42], [43].”
MethodImproving Generalization of Deepfake Detection With Data Farming and Few-Shot Learning
Korshunov, P., & Marcel, S. (2022) · IEEE Transactions on Biometrics, Behavior, and Identity Science · doi:10.1109/tbiom.2022.3143404 · Cited by 50
“Until the latest era of neural networks, most of the techniques for face swapping or facial reenactment were based on similarity searchers between faces or face patches in target and source video and various blending techniques [21], [22], [23], [24], [25].”
BackgroundA Comparative Evaluation of Local Feature Descriptors for DeepFakes Detection
Akhtar, Z., & Dasgupta, D. (2019) · IEEE Conference on Technologies for Homeland Security (HST) · doi:10.1109/hst47167.2019.9033005 · Cited by 54
“Xingjie et al. [25] designed a framework to swap the faces using alpha image blending method.”
Method
Metadata
- Authors
- Xingjie, Z., Song, J., & Park, J.-I.
- Affiliations
- Hanyang University (KR)
- ORCID
- Park, Jong-Il
- Venue
- 2014 4th IEEE International Conference on Network Infrastructure and Digital Content
- Publisher
- IEEE
- Published
- 2014-09
- Pages
- 95-98
- OpenAlex
- W2082926905
- Cited by
- 15
- References
- 6
- Citations by year
- 2026: 1 · 2024: 2 · 2023: 2 · 2022: 1 · 2021: 1 · 2020: 3 · 2019: 3 · 2018: 2
- FWCI
- 0.00
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC) (publishedVersion)
- Funders
- Ministry of Science, ICT and Future Planning
- National IT Industry Promotion Agency
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- face swapping, image blending, image generation, real-time processing, face synthesis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: The image blending method for face swapping. https://app.cochat.ai/papers/10.1109/icnidc.2014.7000272
- The paper
- Xingjie, Z., Song, J., & Park, J.-I. (2014). The image blending method for face swapping. 2014 4th IEEE International Conference on Network Infrastructure and Digital Content. https://doi.org/10.1109/icnidc.2014.7000272
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.