In this paper, a visual focus of attention(VFOA) detection method based on the improved hybrid incremental dynamic Bayesian network(IHIDBN) constructed with the fusion of head, gaze and prediction sub-models is propos...In this paper, a visual focus of attention(VFOA) detection method based on the improved hybrid incremental dynamic Bayesian network(IHIDBN) constructed with the fusion of head, gaze and prediction sub-models is proposed aiming at solving the problem of the complexity and uncertainty in dynamic scenes. Firstly, gaze detection sub-model is improved based on the traditional human eye model to enhance the recognition rate and robustness for different subjects which are detected. Secondly, the related sub-models are described, and conditional probability is used to establish regression models respectively. Also an incremental learning method is used to dynamically update the parameters to improve adaptability of this model. The method has been evaluated on two public datasets and daily exper iments. The results show that the method proposed in this paper can effectively estimate VFOA from user, and it is robust to the free deflection of the head and distance change.展开更多
The information of expression texture extracted by the completed local ternary patterns(CLTP) method is not accurate enough, which may cause low recognition rate. Therefore, an improved completed local ternary pattern...The information of expression texture extracted by the completed local ternary patterns(CLTP) method is not accurate enough, which may cause low recognition rate. Therefore, an improved completed local ternary patterns(ICLTP) is proposed here. Firstly, the Scharr operator is used to calculate gradient magnitudes of images to enhance the detail of texture, which is beneficial to obtaining more accurate expression features. Secondly, two different neighborhoods of CLTP features are combined to obtain much information of facial expression. Finally, K nearest neighbor(KNN) and sparse representation classifier(SRC) are combined for classification and a 10-fold cross-validation method is tested in the JAFFE and CK+ databases. The results show that the ICLTP method can improve the recognition rate of facial expression and reduce the confusion between various expressions. Especially, the misrecognition rate of other six expressions recognized as neutral is reduced in the 7-class expression recognition.展开更多
基金supported by the National Natural Science Foundation of China(No.51604056)the Basic Frontier Research Project of Chongqing(No.cstc2016jcyj A0537)。
文摘In this paper, a visual focus of attention(VFOA) detection method based on the improved hybrid incremental dynamic Bayesian network(IHIDBN) constructed with the fusion of head, gaze and prediction sub-models is proposed aiming at solving the problem of the complexity and uncertainty in dynamic scenes. Firstly, gaze detection sub-model is improved based on the traditional human eye model to enhance the recognition rate and robustness for different subjects which are detected. Secondly, the related sub-models are described, and conditional probability is used to establish regression models respectively. Also an incremental learning method is used to dynamically update the parameters to improve adaptability of this model. The method has been evaluated on two public datasets and daily exper iments. The results show that the method proposed in this paper can effectively estimate VFOA from user, and it is robust to the free deflection of the head and distance change.
基金supported by the National Natural Science Foundation of China(No.51604056)the Chongqing Science and Technology Commission(No.cstc2015jcyjBX0066)
文摘The information of expression texture extracted by the completed local ternary patterns(CLTP) method is not accurate enough, which may cause low recognition rate. Therefore, an improved completed local ternary patterns(ICLTP) is proposed here. Firstly, the Scharr operator is used to calculate gradient magnitudes of images to enhance the detail of texture, which is beneficial to obtaining more accurate expression features. Secondly, two different neighborhoods of CLTP features are combined to obtain much information of facial expression. Finally, K nearest neighbor(KNN) and sparse representation classifier(SRC) are combined for classification and a 10-fold cross-validation method is tested in the JAFFE and CK+ databases. The results show that the ICLTP method can improve the recognition rate of facial expression and reduce the confusion between various expressions. Especially, the misrecognition rate of other six expressions recognized as neutral is reduced in the 7-class expression recognition.
