scholarly journals 3D Face Modeling Algorithm for Film and Television Animation Based on Lightweight Convolutional Neural Network

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Cheng Di ◽  
Jing Peng ◽  
Yihua Di ◽  
Siwei Wu
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Convolutional Neural Network ◽  
Facial Recognition ◽  
Qr Decomposition ◽  
Small Sample ◽  
Feature Extraction Algorithm ◽  
Extraction Algorithm ◽  
The Difference ◽  
Difference Criterion

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.

scholarly journals A Method of Combining Hidden Markov Model and Convolutional Neural Network for the 5G RCS Message Filtering

2021 ◽  
Vol 11 (14) ◽  
pp. 6350
Author(s):  
Bibu Gao ◽  
Wenqiang Zhang
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Convolutional Neural Network ◽  
Hidden Markov ◽  
Short Text ◽  
Feature Extraction Algorithm ◽  
Extraction Algorithm ◽  
Message Service

As one of the 5G applications, rich communication suite (RCS), known as the next generation of Short Message Service (SMS), contains multimedia and interactive information for a better user experience. Meanwhile, the RCS industry worries that spammers may migrate their spamming misdeeds to RCS messages, the complexity of which challenges the filtering technology because each of them contains hundreds of fields with various types of data, such as texts, images and videos. Among the data, the hundreds of fields of text data contain the main content, which is adequate and more efficient for combating spam. This paper first discusses the text fields, which possibly contain spam information, then use the hidden Markov model (HMM) to weight the fields and finally use convolutional neural network (CNN) to classify the RCS messages. In the HMM step, the text fields are treated differently. The short texts of these fields are represented as feature weight sequences extracted by a feature extraction algorithm based on a probability density function. Then, the proposed HMM learns the weight sequence and produces a proper weight for each short text. Other text fields with fewer words are also weighted by the feature extraction algorithm. In the CNN step, all these feature weights first construct the RCS message matrix. The matrices of the training RCS messages are used as the CNN model inputs for learning and the matrices of testing messages are used as the trained CNN model inputs for RCS message property prediction. Four optimization technologies are introduced into the CNN classification process. Promising experiment results are achieved on the real industrial data.

Corresponding Feature Extraction Algorithm between Infrared and Visible Images Using MSER

2011 ◽  
Vol 33 (7) ◽  
pp. 1625-1631 ◽  
Author(s):  
Lin Lian ◽  
Guo-hui Li ◽  
Hai-tao Wang ◽  
hao Tian ◽  
Shu-kui Xu
Keyword(s):  
Feature Extraction ◽  
Feature Extraction Algorithm ◽  
Extraction Algorithm ◽  
Visible Images

Deep convolutional neural networks for human movement detection using wireless signals

2021 ◽  
pp. 1-10
Author(s):  
Chien-Cheng Leea ◽  
Zhongjian Gao ◽  
Xiu-Chi Huanga
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Convolutional Neural Network ◽  
Detection System ◽  
Deep Convolutional Neural Network ◽  
Human Detection ◽  
Two Dimensional ◽  
Dimensional Matrix ◽  
State Classification ◽  
Propagation Paths

This paper proposes a Wi-Fi-based indoor human detection system using a deep convolutional neural network. The system detects different human states in various situations, including different environments and propagation paths. The main improvements proposed by the system is that there is no cameras overhead and no sensors are mounted. This system captures useful amplitude information from the channel state information and converts this information into an image-like two-dimensional matrix. Next, the two-dimensional matrix is used as an input to a deep convolutional neural network (CNN) to distinguish human states. In this work, a deep residual network (ResNet) architecture is used to perform human state classification with hierarchical topological feature extraction. Several combinations of datasets for different environments and propagation paths are used in this study. ResNet’s powerful inference simplifies feature extraction and improves the accuracy of human state classification. The experimental results show that the fine-tuned ResNet-18 model has good performance in indoor human detection, including people not present, people still, and people moving. Compared with traditional machine learning using handcrafted features, this method is simple and effective.

Sign in / Sign up

Export Citation Format

Share Document