Search

Copyright of Journal of Data Acquisition & Processing / Shu Ju Cai Ji Yu Chu Li is the property of Editorial Department of Journal of Nanjing University of Aeronautics & Astronautics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To address the issue of low accuracy in facial expression recognition due to insufficient consideration of semantic features and individual facial characteristics in most current facial expression extraction methods, a highly efficient facial expression recognition method based on feature decoding (FER-FD) is proposed. This method consists of two modules, namely the feature decoupling module (FFD) and the semantic enhancement module (VTS). Firstly, the FFD module employs two deep 2 D convolutional neural networks to extract facial and expression features from input images, where the facial feature decoupler disentangles facial features from expression features to minimize the influence of individual facial characteristics. Secondly, the VTS module adopts two key ideas to automatically capture facial movements in an unsupervised manner, thereby acquiring deep semantic information of the global facial region. Finally, concatenating the features from both modules enables more accurate prediction of facial expressions of samples. Experimental results demonstrate that the proposed feature decoding method achieves 98.78% accuracy on the CK + dataset, exhibiting scalability, adaptability to different scenarios, and good generalization capability. [ABSTRACT FROM AUTHOR]

This paper proposed a robust recognition model FFDNet for facial expression recognition in complex environments with occlusion and pose variation of the face. The algorithm used a multi-scale structure for feature fusion to address the differences in face region scales. It decomposed feature differences and fine-grained by fine-grained modules, and used encoders to capture features with discriminative power and small differences. Furthermore it proposed a diversity feature loss function to drive the model to mine richer fine-grained features. Experimental results show that FFDNet obtains 88.50% and 88.75% accuracy on the RAF-DB and FERPlus datasets, respectively, while outperforming some state-of-the-art models on both occlusion and pose variation datasets. The experimental results demonstrate the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin University of Science & Technology is the property of Journal of Harbin University of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The complex facial expressions and small targets make it difficult for many existing artificial intelligence algorithms to achieve consistent identification. Thus, a multi-stream residual network integrated with an improved Support Vector Machine ( SVM) for facial expression recognition is proposed. The method consists of three steps, namely information enhancement, expression feature extraction and expression classification. First, an adaptive multi-stream information enhancement module is proposed to highlight key image information and enhance feature correlation. Next, a residual interaction module is proposed to extract the spatial information of feature images, highlight facial expression features, and output three feature images with diiferent scales. Last, improved SVM is employed to classify the expression of three-branch feature images to further enhance the robustness of the algorithm. The experimental results show that the accuracy of the proposed method on CK +, FER2013 and JAFFE data sets reaches 98.57%, 77.28% and 96. 4% respectively, all of which are superior to other classic and novel algorithms. Thus, it provides new insights in the recognition of facial expressions by AI. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer-Aided Design & Computer Graphics / Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Aiming at the problems that face images in uncontrollable environments are susceptible to complex factors such as illumination and pose changes, which in turn cause low face detection rate and poor expression recognition accuracy in face expression recognition, an expression recognition method with an embedded attention mechanism residual network is proposed. In the stage of face detection, the improved RetinaFace algorithm is used to complete multi-view face detection and obtain the face region. In the stage of feature extraction, ResNet-50 is used as the backbone network for feature extraction. Firstly, the pre- processed face images are sequentially passed through the channel attention network and spatial attention network of this model to explicitly model the global image interdependence. Secondly, in the shortcut connection of the dashed residual cells, an average ensemble layer is added for the downsampling operation. By fine-tuning the operation of the residual module, the mapping between the input features is enhanced, so that the extracted expression features can be passed between the networks more completely, so as to reduce the loss of feature information. Finally, the convolutional block attention module (CBAM) attention mechanism module is passed into the network again to enhance the channel dimension information and spatial dimension information of local expression features, strengthen the focus information of feature regions with high relevance to expressions in the feature map, and suppress the interference of irrelevant regions in the feature map, thus speeding up the convergence speed of the network and improving the expression recognition rate. Compared with the baseline algorithm, this method achieves 87.65% and 73.57% accuracy on the RAF-DB and FER2013 expression datasets, respectively. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin University of Science & Technology is the property of Journal of Harbin University of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In view of Lhe problems of low raLe of infa nL expression recognilion and Lhe insufficienl exLracLion of complex features, an infant expression recognition algorithm based on MobileNetV2 and Ll3P dual - channel feature fusion is proposed. The first channel uses the improved MobileNetV2 network to quickly and accurately extract the global features of facial expressions. The second channel divides the original input image into blocks, and uses image information entropy to construct weights, and extracts block - weighted LBP histogram features to highlight the regions wiLh rich expression informaLion. The ouLpuL vecLor of Lhe dual - channel model is fused Lo improve Lhe feaLure expression abiliLy, and Lhe supporL vecLor machine is used Lo replace Lhe SofLmax layer for expression classificalion. Experiments show that the use of fusion features has a better classification effect than a single feature, and in the self - built infant expression data set, the accuracy of expression recognition can reach 85. 71 % . [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Facial expression recognition is a further research based on face detection, which is an important research direction in the field of computer vision. The goal of the research is to automatically recognize facial expressions based on micro video and study how to use deep learning technology to assist and promote the development of facial expression recognition technology in a big data environment. A fully automated expression recognition model has been designed to address some of the key technical challenges in the expression intelligence recognition process. The model combines a deep auto-encoding network and a self-attention mechanism to construct a sub-model for automatic extraction of facial expression features, and then the evidence theory is used to fuse the results of multi-feature classification. Experimental results show that the model can significantly improve the accuracy of expression recognition, which has important theoretical significance and research value. [ABSTRACT FROM AUTHOR]

Based on the depth feature of facial micro-expression recognition, such as CNN, the classification method of facial micro -expression recognition is gradually improved. Compared with the traditional feature extraction method, it is easier to meet the real -time application. In order to perfect the details and extract the fine features of micro-expressions, this paper proposed a new algorithm combining the atrous convolutions kernel and the automatic correction of face to improve the feature extraction process of CNN network. It trained and tested the model on CASME and CASME II micro-expression public data sets through real-time recognition in real-time application of automatic face correction. It improved the robustness of the model by comparing the loss function schemes. The accuracy of the method in CASME is 70. 16% and witch in CASME II is 72. 26% . Real-time recognition frame rate at 60 fps. This method can effectively improve the accuracy of micro -expression recognition, meet the real-time requirements, and has good robustness and generalization ability. [ABSTRACT FROM AUTHOR]

Copyright of Chinese Journal of Liquid Crystal & Displays is the property of Chinese Journal of Liquid Crystal & Displays and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In order to improve the detection accuracy of expression recognition technology, a face expression recognition method based on cascade network optimized by SWA is proposed. Compared with a single convolutional network, multi-network cascading reachs higher detection accuracy. With respect to the traditional training method SGD, SWA training method enhances the generalization ability of the sub-network in the cascade network, which further improves the overall performance of the model. By testing on the Fer2013 dataset, the experimental results shows that the detection accuracy of the network cascaded by the way of weighted summation based on SWA training method reachs 74.478%, which is 1.4% higher than the single network model trained by the traditional SGD method. In addition, the improved model proposed in the present study reachs a higher recognition accuracy than other typical methods. [ABSTRACT FROM AUTHOR]

This paper studied the static face image expression recognition method based on deep learning. Firstly, it introduced the principle of deep learning, and summarized the current public and commonly used facial expression data sets. Then it introduced the three steps of expression recognition based on deep learning. It summarized the main methods of image preprocessing and expression classification. This paper mainly summarized the deep learning frameworks with better performance to extract features, the basic principles, advantages and disadvantages of these methods. Finally, the paper pointed out the problems of facial expression recognition and possible future development trends. [ABSTRACT FROM AUTHOR]

Copyright of Information & Control is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Aiming at the problem of how to more efficiently use the distributed features that convolutional neural network has learned from training images, this paper proposed a regions of interest ( ROI) region secondary voting mechanism for facial expression recognition. Firstly, it divided the image into a series of ROI images, which were input into the convolutional neural network for training. Then, it input the ROI images of the test image into the convolutional neural network and got all ROI images' discriminant results. Lastly, it used the secondary voting mechanism to determine the final category of test image . In addition, aiming at the problem of convolutional neural network cannot learn spatial position info rmation such as rotation,this paper introduced the spatial transformer network to make convolutional neural network useful in complex condition. Experiments show the ROI region secondary voting mechanism can more effectively use the distributed features which learned by convolutional neural network, compared with the method of voting directly using ROI images, the accuracy is increased by 1. 1 % . The introduction of STN can effectively improve the robustness of convolutional neural network,compared with non-introduced STN, the accuracy is increased by 1. 5 % . [ABSTRACT FROM AUTHOR]

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Data Acquisition & Processing / Shu Ju Cai Ji Yu Chu Li is the property of Editorial Department of Journal of Nanjing University of Aeronautics & Astronautics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Aiming at the constructed dictionary of traditional sparse representation method with not discrimination enough, this paper researched the construction and classification of discrimination dictionary based on K-SVD algorithm, and proposed a hierarchy structured dictionary learning method. It divided training samples into three parts, which were the eyes and eyebrows together, cheeks and mouth. It used K-SVD algorithm to obtain the block dictionary vectors for the divided three parts. It calculated the weight of block dictionary vectors by the weight assignment of AHF method, and then constructed sub-dictionary of each expression. At last, it combined all the constructed sub-dictionaries and used structured dictionary learning algorithm for solving. The classification of the test samples depended on the effect of the reconstruction. Experimental results show that the proposed method has guaranteed dictionary discrimination and also has a higher recognition rate by using JAFFE and CK database. [ABSTRACT FROM AUTHOR]

In order to reduce the effect of appearance,pose,glasses and non-uniform expression definition to facial expression recognition,this paper proposed a collaborative facial expression recognition algorithm based on facial appearance independently discrimination. Firstly,it selected an automatic facial landmark detection algorithm to localize and align the face region of each frame,and the peak expression faces from the video face sequence. Then,it generated an intra class variation face using the peak expression face and training expression faces of an expression class,and realized the expression representation by computing the difference information between intra class variation face and peak expression face. Lastly,it adopted sparsity based classification and expression representation to decide the labels of each face expression. Simulation experimental results based on European and American faces and Asian faces show that the proposed algorithm performs better expression recognition accuracy,at the same time it shows good recognition performance to faces of different appearances and faces wearing glasses. [ABSTRACT FROM AUTHOR]

Copyright of Acta Automatica Sinica is the property of Chinese Academy of Sciences, Institute of Automation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)