Face recognition based on two dimensional locality preserving projections in frequency domain

Lu, Chong; Liu, Xiaodong; Liu, Wanquan

doi:10.1016/j.neucom.2011.08.045

Cited by 13 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be noted that this paper is an extended version of our study [18] and previous works [15][19] [21]. In ref.…”

Section: Introductionmentioning

confidence: 83%

“…(2) Project B t onto optimal projection matrices R and C as equations (21), (22), (23) to get structure information as feature matrix Y t . (3) Compute the Euclidean distance from the Y t testing image to each k-th (k = 1, 2…, N) training image with the below equation (24) and the threshold T to decide the label of testing image.…”

Section: Classificationmentioning

confidence: 99%

“…In ref [15], Gao et al proposed an extended technique of classical 2D-PCA method called fractional 2D-PCA for face recognition. Some other authors in ref [19] [21] proposed a fusion of DCT with 2D-LPP or 2D-PCA for face recognition. Based on these models, we proposed a hybrid multi-techniques scheme in order to improve performance recognition in facial expression representation problem.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On approaching 2D-FPCA technique to improve image representation in frequency domain

Truong

Thanh

et al. 2013

Proceedings of the Fourth Symposium on Information and Communication Technology - SoICT '13

View full text Add to dashboard Cite

A novel approach based on structure information extraction in frequency domain is proposed for image representation problem. Regarding this problem, a new subspace method based on Twodimensional Fractional Principle Component Analysis (2D-FPCA) in frequency domain is applied to images, thus extracting the texture information. In order to extract the structure information, the system utilizes this new subspace as the bilateral consideration of 2D-FPCA technique called B2D-FPCA. For this purpose: (1) we first introduce the theory of 2D-FPCA based on the definition of fractional variance and fractional covariance matrix; (2) then show its improvement called Bilateral 2D-FPCA and (3) the robustness of 2D-DCT is also described as the preprocessing step. This approach is applied to facial expression representation problem to prove the stability and robustness of the proposed framework. For demonstration, facial expressions datasets (JAFFE, Pain expression subset and Cohn-Kanade) are used in order to compare the proposed framework with some other approaches.

show abstract

“…It should be noted that this paper is an extended version of our study [18] and previous works [15][19] [21]. In ref.…”

Section: Introductionmentioning

confidence: 83%

Section: Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On approaching 2D-FPCA technique to improve image representation in frequency domain

Truong

Thanh

et al. 2013

Proceedings of the Fourth Symposium on Information and Communication Technology - SoICT '13

View full text Add to dashboard Cite

show abstract

“…Uç ar et al [3] designed a radial basis function (RBF) network, capable of mining the correlation between the motion patterns of facial features and human facial expressions, and applied the trained network to analyze facial expressions. Lu et al [4] transformed face images into eigenvectors for twodimensional (2D) discrete cosine transform, and treated single-layer feedforward neural network as the classifier, aiming to improve the generalization and classification of facial expressions. Lee and Ro [5] created a novel feature of facial expressions, which encodes the amplitude and direction of the edges of the region of interest (ROI) to express different facial expression features, and demonstrated that the feature is highly robust to noise and illumination changes.…”

Section: Literature Reviewmentioning

confidence: 99%

A Facial Expression Recognition Model Based on Texture and Shape Features

Li¹,

An²,

Che³

2020

View full text Add to dashboard Cite

With the development of computer vision, facial expression recognition has become a research hotspot. To further improve the accuracy of facial expression recognition, this paper probes deep into image segmentation, feature extraction, and facial expression classification. Firstly, the convolution neural network (CNN) was adopted to accurately separate the salient regions from the face image. Next, the Gaussian Markov random field (GMRF) model was improved to enhance the ability of texture features to represent image information, and a novel feature extraction algorithm called specific angle abundance entropy (SAAE) was designed to improve the representation ability of shape features. After that, the texture features were combined with shape features, and trained and classified by the support vector machine (SVM) classifier. Finally, the proposed method was compared with common methods of facial expression recognition on a standard facial expression database. The results show that our method can greatly improve the accuracy of facial expression recognition.

show abstract

“…In order to overcome this limitation, 2DLPP is put forward. Its principal idea is to compute the covariance matrix based on two dimensional original [3] training image matrices, and to obtain its optimal projection matrix iteratively [4,5].…”

Section: Introductionmentioning

confidence: 99%

Face Recognition Algorithm Using Two Dimensional Locality Preserving Projection in Discrete Wavelet Domain

Lu¹,

Su²

2015

TOAUTOCJ

View full text Add to dashboard Cite

This paper proposes a new method for face recognition using Two Dimensional Locality Preserving Projection (2DLPP) in Discrete Wavelet Domain (DWT). Firstly, the dimensionality of the original face image is reduced by using the discrete wavelets transform and low frequency channel (LL) is selected to be as the features of face image. And then 2DLPP is applied to decrease the dimension of LL. Finally, the nearest neighbour classifier is used for face classification. The experiment results on ORL face database demonstrate the effectiveness of the proposed method.

show abstract

Face recognition based on two dimensional locality preserving projections in frequency domain

Cited by 13 publications

References 32 publications

On approaching 2D-FPCA technique to improve image representation in frequency domain

On approaching 2D-FPCA technique to improve image representation in frequency domain

A Facial Expression Recognition Model Based on Texture and Shape Features

Face Recognition Algorithm Using Two Dimensional Locality Preserving Projection in Discrete Wavelet Domain

Contact Info

Product

Resources

About