The scale of deer breeding has gradually increased in recent years and better information management is necessary,which requires the identification of individual deer.In this paper,a deer face dataset is produced usin...The scale of deer breeding has gradually increased in recent years and better information management is necessary,which requires the identification of individual deer.In this paper,a deer face dataset is produced using face images obtained from different angles,and an improved residual neural network(ResNet)-based recognition model is proposed to extract the features of deer faces,which have high similarity.The model is based on ResNet-50,which reduces the depth of the model,and the network depth is only 29 layers;the model connects Squeeze-and-Excitation(SE)modules at each of the four layers where the channel changes to improve the quality of features by compressing the feature information extracted through the entire layer.A maximum pooling layer is used in the ResBlock shortcut connection to reduce the information loss caused by messages passing through the ResBlock.The Rectified Linear Unit(ReLU)activation function in the network is replaced by the Exponential Linear Unit(ELU)activation function to reduce information loss during forward propagation of the network.The preprocessed 6864 sika deer face dataset was used to train the recognition model based on SEResnet,which is demonstrated to identify individuals accurately.By setting up comparative experiments under different structures,the model reduces the amount of parameters,ensures the accuracy of the model,and improves the calculation speed of the model.Using the improved method in this paper to compare with the classical model and facial recognition models of different animals,the results show that the recognition effect of this research method is the best,with an average recognition accuracy of 97.48%.The sika deer face recognition model proposed in this study is effective.The results contribute to the practical application of animal facial recognition technology in the breeding of sika deer and other animals with few distinct facial features.展开更多
This paper presents a rheology-based approach to animate realistic face model. The dynamic and biorheological characteristics of the force member （muscles） and stressed member （face） are considered. The stressed f...This paper presents a rheology-based approach to animate realistic face model. The dynamic and biorheological characteristics of the force member （muscles） and stressed member （face） are considered. The stressed face can be modeled as viscoelastic bodies with the Hooke bodies and Newton bodies connected in a composite series-parallel manner. Then, the stress-strain relationship is derived, and the constitutive equations established. Using these constitutive equations, the face model can be animated with the force generated by muscles. Experimental results show that this method can realistically simulate the mechanical properties and motion characteristics of human face, and performance of this method is satisfactory.展开更多
Active Shape Model （ASM） is a powerful statistical tool to extract the facial features of a face image under frontal view. It mainly relies on Principle Component Analysis （PCA） to statistically model the variabil...Active Shape Model （ASM） is a powerful statistical tool to extract the facial features of a face image under frontal view. It mainly relies on Principle Component Analysis （PCA） to statistically model the variability in the training set of example shapes. Independent Component Analysis （ICA） has been proven to be more efficient to extract face features than PCA. In this paper, we combine the PCA and ICA by the consecutive strategy to form a novel ASM. Firstly, an initial model, which shows the global shape variability in the training set, is generated by the PCA-based ASM. And then, the final shape model, which contains more local characters, is established by the ICA-based ASM. Experimental results verify that the accuracy of facial feature extraction is statistically significantly improved by applying the ICA modes after the PCA modes.展开更多
In expression recognition, feature representation is critical for successful recognition since it contains distinctive information of expressions. In this paper, a new approach for representing facial expression featu...In expression recognition, feature representation is critical for successful recognition since it contains distinctive information of expressions. In this paper, a new approach for representing facial expression features is proposed with its objective to describe features in an effective and efficient way in order to improve the recognition performance. The method combines the facial action coding system(FACS) and 'uniform' local binary patterns(LBP) to represent facial expression features from coarse to fine. The facial feature regions are extracted by active shape models(ASM) based on FACS to obtain the gray-level texture. Then, LBP is used to represent expression features for enhancing the discriminant. A facial expression recognition system is developed based on this feature extraction method by using K nearest neighborhood(K-NN) classifier to recognize facial expressions. Finally, experiments are carried out to evaluate this feature extraction method. The significance of removing the unrelated facial regions and enhancing the discrimination ability of expression features in the recognition process is indicated by the results, in addition to its convenience.展开更多
Emotion Model is the basis of facial expression recognition system. The constructed emotional model should not only match facial expressions with emotions, but also reflect the location relationship between different ...Emotion Model is the basis of facial expression recognition system. The constructed emotional model should not only match facial expressions with emotions, but also reflect the location relationship between different emotions. In this way, it is easy to understand the current emotion of an individual through the analysis of the acquired facial expression information. This paper constructs an improved three-dimensional model for emotion based on fuzzy theory, which corresponds to the facial features to emotions based on the basic emotions proposed by Ekman. What’s more, the three-dimensional model for motion is able to divide every emotion into three different groups which can show the positional relationship visually and quantitatively and at the same time determine the degree of emotion based on fuzzy theory.展开更多
This paper proposes a technique for synthesizing a pixel-based photo-realistic talking face animation using two-step synthesis with HMMs and DNNs. We introduce facial expression parameters as an intermediate represent...This paper proposes a technique for synthesizing a pixel-based photo-realistic talking face animation using two-step synthesis with HMMs and DNNs. We introduce facial expression parameters as an intermediate representation that has a good correspondence with both of the input contexts and the output pixel data of face images. The sequences of the facial expression parameters are modeled using context-dependent HMMs with static and dynamic features. The mapping from the expression parameters to the target pixel images are trained using DNNs. We examine the required amount of the training data for HMMs and DNNs and compare the performance of the proposed technique with the conventional PCA-based technique through objective and subjective evaluation experiments.展开更多
基金This research was supported by the Science and Technology Department of Jilin Province[20210202128NC http://kjt.jl.gov.cn]The People’s Republic of China Ministry of Science and Technology[2018YFF0213606-03 http://www.most.gov.cn]+1 种基金the Jilin Province Development and Reform Commission[2019C021 http://jldrc.jl.gov.cn]the Science and Technology Bureau of Changchun City[21ZGN27 http://kjj.changchun.gov.cn].
文摘The scale of deer breeding has gradually increased in recent years and better information management is necessary,which requires the identification of individual deer.In this paper,a deer face dataset is produced using face images obtained from different angles,and an improved residual neural network(ResNet)-based recognition model is proposed to extract the features of deer faces,which have high similarity.The model is based on ResNet-50,which reduces the depth of the model,and the network depth is only 29 layers;the model connects Squeeze-and-Excitation(SE)modules at each of the four layers where the channel changes to improve the quality of features by compressing the feature information extracted through the entire layer.A maximum pooling layer is used in the ResBlock shortcut connection to reduce the information loss caused by messages passing through the ResBlock.The Rectified Linear Unit(ReLU)activation function in the network is replaced by the Exponential Linear Unit(ELU)activation function to reduce information loss during forward propagation of the network.The preprocessed 6864 sika deer face dataset was used to train the recognition model based on SEResnet,which is demonstrated to identify individuals accurately.By setting up comparative experiments under different structures,the model reduces the amount of parameters,ensures the accuracy of the model,and improves the calculation speed of the model.Using the improved method in this paper to compare with the classical model and facial recognition models of different animals,the results show that the recognition effect of this research method is the best,with an average recognition accuracy of 97.48%.The sika deer face recognition model proposed in this study is effective.The results contribute to the practical application of animal facial recognition technology in the breeding of sika deer and other animals with few distinct facial features.
基金Project supported by the National Natural Science Foundation of China (Grant No.60772124)the Shanghai Leading Academic Discipline Project (Grant No.S30108)the Outstanding Young Teachers in University Foundation of Shanghai (Grant No.B37010708003)
文摘This paper presents a rheology-based approach to animate realistic face model. The dynamic and biorheological characteristics of the force member （muscles） and stressed member （face） are considered. The stressed face can be modeled as viscoelastic bodies with the Hooke bodies and Newton bodies connected in a composite series-parallel manner. Then, the stress-strain relationship is derived, and the constitutive equations established. Using these constitutive equations, the face model can be animated with the force generated by muscles. Experimental results show that this method can realistically simulate the mechanical properties and motion characteristics of human face, and performance of this method is satisfactory.
文摘Active Shape Model （ASM） is a powerful statistical tool to extract the facial features of a face image under frontal view. It mainly relies on Principle Component Analysis （PCA） to statistically model the variability in the training set of example shapes. Independent Component Analysis （ICA） has been proven to be more efficient to extract face features than PCA. In this paper, we combine the PCA and ICA by the consecutive strategy to form a novel ASM. Firstly, an initial model, which shows the global shape variability in the training set, is generated by the PCA-based ASM. And then, the final shape model, which contains more local characters, is established by the ICA-based ASM. Experimental results verify that the accuracy of facial feature extraction is statistically significantly improved by applying the ICA modes after the PCA modes.
基金supported by National Natural Science Foundation of China(No.61273339)
文摘In expression recognition, feature representation is critical for successful recognition since it contains distinctive information of expressions. In this paper, a new approach for representing facial expression features is proposed with its objective to describe features in an effective and efficient way in order to improve the recognition performance. The method combines the facial action coding system(FACS) and 'uniform' local binary patterns(LBP) to represent facial expression features from coarse to fine. The facial feature regions are extracted by active shape models(ASM) based on FACS to obtain the gray-level texture. Then, LBP is used to represent expression features for enhancing the discriminant. A facial expression recognition system is developed based on this feature extraction method by using K nearest neighborhood(K-NN) classifier to recognize facial expressions. Finally, experiments are carried out to evaluate this feature extraction method. The significance of removing the unrelated facial regions and enhancing the discrimination ability of expression features in the recognition process is indicated by the results, in addition to its convenience.
文摘Emotion Model is the basis of facial expression recognition system. The constructed emotional model should not only match facial expressions with emotions, but also reflect the location relationship between different emotions. In this way, it is easy to understand the current emotion of an individual through the analysis of the acquired facial expression information. This paper constructs an improved three-dimensional model for emotion based on fuzzy theory, which corresponds to the facial features to emotions based on the basic emotions proposed by Ekman. What’s more, the three-dimensional model for motion is able to divide every emotion into three different groups which can show the positional relationship visually and quantitatively and at the same time determine the degree of emotion based on fuzzy theory.
基金Supported by National Natural Science Foundation of China（61303150,61472393） China Postdoctoral Science Foundation（2012M521248） Anhui Province Innovative Funds on Intelligent Speech Technology and Industrialization（13Z02008）
文摘This paper proposes a technique for synthesizing a pixel-based photo-realistic talking face animation using two-step synthesis with HMMs and DNNs. We introduce facial expression parameters as an intermediate representation that has a good correspondence with both of the input contexts and the output pixel data of face images. The sequences of the facial expression parameters are modeled using context-dependent HMMs with static and dynamic features. The mapping from the expression parameters to the target pixel images are trained using DNNs. We examine the required amount of the training data for HMMs and DNNs and compare the performance of the proposed technique with the conventional PCA-based technique through objective and subjective evaluation experiments.
