Manifold based Sparse Representation for robust expression recognition without neutral subtraction

Ptucha, Raymond; Tsagkatakis, Grigorios; Savakis, Andreas

doi:10.1109/iccvw.2011.6130512

Cited by 46 publications

(34 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sparse representation methods include K-SVD [28], LC-KSVD1 and LC-KSVD2 [12]. The combined methods include Sparse Representation-based Classification (SRC) [15], Manifold based Sparse Representation (MSR) [19], and our proposed K-LGE method.…”

Section: Methodsmentioning

confidence: 99%

“…Test samples use the m element dictionary to generate sparse coefficients using (10). These sparse coefficients are converted to a class estimate using (19). LC-KSVD1 modifies the K-SVD objective function to favor clustering of coefficients by class and LC-KSVD2 further modifies the K-SVD objective function to include the solution of coefficient transformation matrix C.…”

Section: B Testing Methodologiesmentioning

confidence: 99%

“…The work in [18] struggled with coefficient contamination, noting that applying Wright's framework is not a straightforward process. Ptucha et al [19] addressed the coefficient contamination problem by preprocessing the data with supervised manifold learning. Similarly to subspace clustering [20], supervision in manifold learning encourages clustering of sample images in accordance with their classification labels.…”

Section: Introductionmentioning

confidence: 99%

“…In [19] it was sown that supervised dimensionality reduction minimizes SR coefficient contamination by enforcing class separation. A discriminative dictionary was utilized in [12,21,22,32], but we find similar results at much faster runtimes by doing class discrimination and dimensionality reduction prior to dictionary learning.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Joint optimization of manifold learning and sparse representations

Ptucha

Savakis

2013

2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

Self Cite

View full text Add to dashboard Cite

Dimensionality reduction via manifold learning offers an elegant representation of data whereby the high dimensional feature space is parameterized by a lower dimensional space where the data resides.Sparse representations efficiently represent test patterns by sparse linear coefficients from a dictionary of training exemplars. Sparse representations have been adopted for classification purposes, but the resulting classifiers may have to deal with data in high dimensions and large dictionaries. This paper analyzes the interaction between dimensionality reduction and sparse representations.The proposed technique, called K-LGE, presents a unified framework which utilizes a semi-supervised variant of Linear extension of Graph Embedding with K-SVD dictionary learning. An iterative procedure optimizes the dimensionality reduction matrix, sparse representation dictionary, sparse coefficients, and linear classifier. Results are demonstrated in a wide variety of facial and activity recognition problems to demonstrate the robustness of our proposed method.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: B Testing Methodologiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Joint optimization of manifold learning and sparse representations

Ptucha

Savakis

2013

2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The problem has many applications in the field of computer science, medicine, psychology, and other related areas. Part of the research on this problem is focused on recognizing facial expressions from static images [24,22,28,21,15,5,3,2,41]. Although this approach is effective in extracting spatial information, it fails to capture morphological and contextual variations of the expression process.…”

Section: Introductionmentioning

confidence: 99%

LBVCNN: Local Binary Volume Convolutional Neural Network for Facial Expression Recognition From Image Sequences

Kumawat

Verma

Raman

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Recognizing facial expressions is one of the central problems in computer vision. Temporal image sequences have useful spatio-temporal features for recognizing expressions. In this paper, we propose a new 3D Convolution Neural Network (CNN) that can be trained end-to-end for facial expression recognition on temporal image sequences without using facial landmarks. More specifically, a novel 3D convolutional layer that we call Local Binary Volume (LBV) layer is proposed. The LBV layer, when used with our newly proposed LBVCNN network, achieve comparable results compared to state-of-the-art landmark-based or without landmark-based models on image sequences from CK+, Oulu-CASIA, and UNBC McMaster shoulder pain datasets. Furthermore, our LBV layer reduces the number of trainable parameters by a significant amount when compared to a conventional 3D convolutional layer. As a matter of fact, when compared to a 3 × 3 × 3 conventional 3D convolutional layer, the LBV layer uses 27 times less trainable parameters.

show abstract

Expression of Concern: Facial feature discovery for ethnicity recognition

Wang

Zhang

Liu³

et al. 2018

WIREs Data Min & Knowl

View full text Add to dashboard Cite

The salient facial feature discovery is one of the important research tasks in ethnical group face recognition. In this paper, we first construct an ethnical group face dataset including Chinese Uyghur, Tibetan, and Korean. Then, we show that the effective sparse sensing approach to general face recognition is not working anymore for ethnical group facial recognition if the features based on whole face image are used. This is partially due to a fact that each ethnical group may have its own characteristics manifesting only in specified face regions. Therefore, we will analyze the particularity of three ethnical groups and aim to find the common characterizations in some local regions for the three ethnical groups. For this purpose, we first use the facial landmark detector STASM to find some important landmarks in a face image, then, we use the well‐known data mining technique, the mRMR algorithm, to select the salient geometric length features based on all possible lines connected by any two landmarks. Second, based on these selected salient features, we construct three “T” regions in a face image for ethnical feature representation and prove them to be effective areas for ethnicity recognition. Finally, some extensive experiments are conducted and the results reveal that the proposed “T” regions with extracted features are quite effective for ethnical group facial recognition when the L2‐norm is adopted using the sparse sensing approach. In comparison to face recognition, the proposed three “T” regions are evaluated on the olivetti research laboratory face dataset, and the results show that the constructed “T” regions for ethnicity recognition are not suitable for general face recognition. This article is categorized under: Algorithmic Development > Structure Discovery Algorithmic Development > Biological Data Mining Fundamental Concepts of Data and Knowledge > Knowledge Representation Technologies > Classification

show abstract

Manifold based Sparse Representation for robust expression recognition without neutral subtraction

Cited by 46 publications

References 20 publications

Joint optimization of manifold learning and sparse representations

Joint optimization of manifold learning and sparse representations

LBVCNN: Local Binary Volume Convolutional Neural Network for Facial Expression Recognition From Image Sequences

Expression of Concern: Facial feature discovery for ethnicity recognition

Contact Info

Product

Resources

About