A novel fusion method of improved adaptive LTP and two-directional two-dimensional PCA for face feature extraction
|
摘要
In this paper, under different illuminations and random noises, focusing on the local texture feature's defects of a face image that cannot be completely described because the threshold of local ternary pattern(LTP) cannot be calculated adaptively, a local three-value model of improved adaptive local ternary pattern(IALTP) is proposed. Firstly, the difference function between the center pixel and the neighborhood pixel weight is established to obtain the statistical characteristics of the central pixel and the neighborhood pixel. Secondly, the adaptively gradient descent iterative function is established to calculate the difference coefficient which is defined to be the threshold of the IALTP operator. Finally, the mean and standard deviation of the pixel weight of the local region are used as the coding mode of IALTP. In order to reflect the overall properties of the face and reduce the dimension of features, the two-directional two-dimensional PCA((2D)~2 PCA) is adopted. The IALTP is used to extract local texture features of eyes and mouth area. After combining the global features and local features, the fusion features(IALTP+) are obtained. The experimental results on the Extended Yale B and AR standard face databases indicate that under different illuminations and random noises, the algorithm proposed in this paper is more robust than others, and the feature's dimension is smaller. The shortest running time reaches 0.329 6 s, and the highest recognition rate reaches 97.39%.
In this paper, under different illuminations and random noises, focusing on the local texture feature's defects of a face image that cannot be completely described because the threshold of local ternary pattern(LTP) cannot be calculated adaptively, a local three-value model of improved adaptive local ternary pattern(IALTP) is proposed. Firstly, the difference function between the center pixel and the neighborhood pixel weight is established to obtain the statistical characteristics of the central pixel and the neighborhood pixel. Secondly, the adaptively gradient descent iterative function is established to calculate the difference coefficient which is defined to be the threshold of the IALTP operator. Finally, the mean and standard deviation of the pixel weight of the local region are used as the coding mode of IALTP. In order to reflect the overall properties of the face and reduce the dimension of features, the two-directional two-dimensional PCA((2D)~2 PCA) is adopted. The IALTP is used to extract local texture features of eyes and mouth area. After combining the global features and local features, the fusion features(IALTP+) are obtained. The experimental results on the Extended Yale B and AR standard face databases indicate that under different illuminations and random noises, the algorithm proposed in this paper is more robust than others, and the feature's dimension is smaller. The shortest running time reaches 0.329 6 s, and the highest recognition rate reaches 97.39%.
In this paper, under different illuminations and random noises, focusing on the local texture feature's defects of a face image that cannot be completely described because the threshold of local ternary pattern(LTP) cannot be calculated adaptively, a local three-value model of improved adaptive local ternary pattern(IALTP) is proposed. Firstly, the difference function between the center pixel and the neighborhood pixel weight is established to obtain the statistical characteristics of the central pixel and the neighborhood pixel. Secondly, the adaptively gradient descent iterative function is established to calculate the difference coefficient which is defined to be the threshold of the IALTP operator. Finally, the mean and standard deviation of the pixel weight of the local region are used as the coding mode of IALTP. In order to reflect the overall properties of the face and reduce the dimension of features, the two-directional two-dimensional PCA((2D)~2 PCA) is adopted. The IALTP is used to extract local texture features of eyes and mouth area. After combining the global features and local features, the fusion features(IALTP+) are obtained. The experimental results on the Extended Yale B and AR standard face databases indicate that under different illuminations and random noises, the algorithm proposed in this paper is more robust than others, and the feature's dimension is smaller. The shortest running time reaches 0.329 6 s, and the highest recognition rate reaches 97.39%.
引文
[1]Hua G,Yang M H and Learnedmiller E,IEEE Transactions on Pattern Analysis&Machine Intelligence 33,1921(2011).
[2]Mashhoori A and Jahromi M Z,Neurocomputing 108,111(2013).
[3]Tasnim Tarannum and Anwesha Paul,Human Expression Recognition based on Facial Features,IEEE Computer Society Conference on Electronics and Vision,990(2016).
[4]Lei Z,Ahonen T and Pietik?inen M,Local Frequency Descriptor for Low-resolution Face Recognition,IEEE International Conference on Automatic Face&Gesture Recognition and Workshops,161(2011).
[5]Ibrahim M,Efat A and Kayesh H,Dynamic Local Ternary Pattern for Face Recognition and Verification,International Conference on Computer Engineering and Applications,2014.
[6]Ruby A U and Chandran J G C,A Theoretical Approach on Face Recognition with Single Sample per Class using CS-LBP and Gabor Magnitude and Phase,2016.
[7]Ren J,Jiang X and Yuan J,Relaxed Local Ternary Pattern for Face Recognition,IEEE International Conference on Image Processing,3680(2013).
[8]Raja G M and Sadasivam V,Journal of Electrical Engineering&Technology 12,402(2017).
[2]Mashhoori A and Jahromi M Z,Neurocomputing 108,111(2013).
[3]Tasnim Tarannum and Anwesha Paul,Human Expression Recognition based on Facial Features,IEEE Computer Society Conference on Electronics and Vision,990(2016).
[4]Lei Z,Ahonen T and Pietik?inen M,Local Frequency Descriptor for Low-resolution Face Recognition,IEEE International Conference on Automatic Face&Gesture Recognition and Workshops,161(2011).
[5]Ibrahim M,Efat A and Kayesh H,Dynamic Local Ternary Pattern for Face Recognition and Verification,International Conference on Computer Engineering and Applications,2014.
[6]Ruby A U and Chandran J G C,A Theoretical Approach on Face Recognition with Single Sample per Class using CS-LBP and Gabor Magnitude and Phase,2016.
[7]Ren J,Jiang X and Yuan J,Relaxed Local Ternary Pattern for Face Recognition,IEEE International Conference on Image Processing,3680(2013).
[8]Raja G M and Sadasivam V,Journal of Electrical Engineering&Technology 12,402(2017).