3D Face Modeling Algorithm for Film and Television Animation Based on Lightweight Convolutional Neural Network
Through the analysis of facial feature extraction technology, this paper designs a lightweight convolutional neural network (LW-CNN). The LW-CNN model adopts a separable convolution structure, which can propose more accurate features with fewer parameters and can extract 3D feature points of a human...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/6752120 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832547738124812288 |
|---|---|
| author | Cheng Di Jing Peng Yihua Di Siwei Wu |
| author_facet | Cheng Di Jing Peng Yihua Di Siwei Wu |
| author_sort | Cheng Di |
| collection | DOAJ |
| description | Through the analysis of facial feature extraction technology, this paper designs a lightweight convolutional neural network (LW-CNN). The LW-CNN model adopts a separable convolution structure, which can propose more accurate features with fewer parameters and can extract 3D feature points of a human face. In order to enhance the accuracy of feature extraction, a face detection method based on the inverted triangle structure is used to detect the face frame of the images in the training set before the model extracts the features. Aiming at the problem that the feature extraction algorithm based on the difference criterion cannot effectively extract the discriminative information, the Generalized Multiple Maximum Dispersion Difference Criterion (GMMSD) and the corresponding feature extraction algorithm are proposed. The algorithm uses the difference criterion instead of the entropy criterion to avoid the “small sample” problem, and the use of QR decomposition can extract more effective discriminative features for facial recognition, while also reducing the computational complexity of feature extraction. Compared with traditional feature extraction methods, GMMSD avoids the problem of “small samples” and does not require preprocessing steps on the samples; it uses QR decomposition to extract features from the original samples and retains the distribution characteristics of the original samples. According to different change matrices, GMMSD can evolve into different feature extraction algorithms, which shows the generalized characteristics of GMMSD. Experiments show that GMMSD can effectively extract facial identification features and improve the accuracy of facial recognition. |
| format | Article |
| id | doaj-art-cfe184231e904cc089b6c50619712a45 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-cfe184231e904cc089b6c50619712a452025-02-03T06:43:46ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/675212067521203D Face Modeling Algorithm for Film and Television Animation Based on Lightweight Convolutional Neural NetworkCheng Di0Jing Peng1Yihua Di2Siwei Wu3School of Arts and Communication, China University of Geosciences, Wuhan 430074, ChinaSchool of Arts and Communication, China University of Geosciences, Wuhan 430074, ChinaCollege of Mechanical and Electrical Engineering, Wuhan Textile University, Wuhan 430074, ChinaSchool of Arts and Communication, China University of Geosciences, Wuhan 430074, ChinaThrough the analysis of facial feature extraction technology, this paper designs a lightweight convolutional neural network (LW-CNN). The LW-CNN model adopts a separable convolution structure, which can propose more accurate features with fewer parameters and can extract 3D feature points of a human face. In order to enhance the accuracy of feature extraction, a face detection method based on the inverted triangle structure is used to detect the face frame of the images in the training set before the model extracts the features. Aiming at the problem that the feature extraction algorithm based on the difference criterion cannot effectively extract the discriminative information, the Generalized Multiple Maximum Dispersion Difference Criterion (GMMSD) and the corresponding feature extraction algorithm are proposed. The algorithm uses the difference criterion instead of the entropy criterion to avoid the “small sample” problem, and the use of QR decomposition can extract more effective discriminative features for facial recognition, while also reducing the computational complexity of feature extraction. Compared with traditional feature extraction methods, GMMSD avoids the problem of “small samples” and does not require preprocessing steps on the samples; it uses QR decomposition to extract features from the original samples and retains the distribution characteristics of the original samples. According to different change matrices, GMMSD can evolve into different feature extraction algorithms, which shows the generalized characteristics of GMMSD. Experiments show that GMMSD can effectively extract facial identification features and improve the accuracy of facial recognition.http://dx.doi.org/10.1155/2021/6752120 |
| spellingShingle | Cheng Di Jing Peng Yihua Di Siwei Wu 3D Face Modeling Algorithm for Film and Television Animation Based on Lightweight Convolutional Neural Network Complexity |
| title | 3D Face Modeling Algorithm for Film and Television Animation Based on Lightweight Convolutional Neural Network |
| title_full | 3D Face Modeling Algorithm for Film and Television Animation Based on Lightweight Convolutional Neural Network |
| title_fullStr | 3D Face Modeling Algorithm for Film and Television Animation Based on Lightweight Convolutional Neural Network |
| title_full_unstemmed | 3D Face Modeling Algorithm for Film and Television Animation Based on Lightweight Convolutional Neural Network |
| title_short | 3D Face Modeling Algorithm for Film and Television Animation Based on Lightweight Convolutional Neural Network |
| title_sort | 3d face modeling algorithm for film and television animation based on lightweight convolutional neural network |
| url | http://dx.doi.org/10.1155/2021/6752120 |
| work_keys_str_mv | AT chengdi 3dfacemodelingalgorithmforfilmandtelevisionanimationbasedonlightweightconvolutionalneuralnetwork AT jingpeng 3dfacemodelingalgorithmforfilmandtelevisionanimationbasedonlightweightconvolutionalneuralnetwork AT yihuadi 3dfacemodelingalgorithmforfilmandtelevisionanimationbasedonlightweightconvolutionalneuralnetwork AT siweiwu 3dfacemodelingalgorithmforfilmandtelevisionanimationbasedonlightweightconvolutionalneuralnetwork |