2021
DOI: 10.1016/j.cmpb.2021.105928
|View full text |Cite
|
Sign up to set email alerts
|

On construction of transfer learning for facial symmetry assessment before and after orthognathic surgery

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

2
17
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
4
1

Relationship

1
8

Authors

Journals

citations
Cited by 35 publications
(19 citation statements)
references
References 32 publications
2
17
0
Order By: Relevance
“…According to the publication by Zhang et al [ 29 , 30 ], the degree of facial symmetry is judged through transfer learning, the contour map of the face is used as training data, and the system can be constructed to classify and score the symmetry of the face. Through the transfer of the Xception model, the classification can achieve an accuracy of 90.6%.…”
Section: Methodsmentioning
confidence: 99%
“…According to the publication by Zhang et al [ 29 , 30 ], the degree of facial symmetry is judged through transfer learning, the contour map of the face is used as training data, and the system can be constructed to classify and score the symmetry of the face. Through the transfer of the Xception model, the classification can achieve an accuracy of 90.6%.…”
Section: Methodsmentioning
confidence: 99%
“…The authors used a handcrafted feature Gabor surface feature (GSF) for Patch Attention Layer (PAL) in their CNN to achieve State-of-the-art in facial expression recognition on the CK+, Oulu-CASIA, and JAFFE datasets. Using effective transfering learning to build CNN model for orthognathic surgery on 3D face image gain high results (Lin et al, 2021). Besides general FAL, a survey about face hallucination presented a comprehensive review of DL techniques in face super-resolution (Jiang et al, 2021).…”
Section: Combining Methodsmentioning
confidence: 99%
“…B. proposed two methods "attribute enhanced sparse codeword" and "attribute embedded inverted indexing" for AL on LFW and Pubfig to improve MAP for large-scale face retrieval. Lin et al (2014) In the next section, we will present DL methods which is the most important contribution of attribute learning.…”
Section: Bayesianmentioning
confidence: 99%
“…Special two-dimensional contour maps converted from CBCTs were considered as the input data. These maps contain much three-dimensional information ( Lin et al, 2021 ). Jeong et al studied the front and side faces of more than 800 subjects with dentofacial dysmorphosis/malocclusion using CNNs and found that CNNs are able to relatively accurately estimate the soft tissue contours related to orthognathic surgery with these photographs alone ( Jeong et al, 2020 ).…”
Section: Applications Of ML In the Dental Oral And Craniofacial Imaging Fieldmentioning
confidence: 99%