Robust automatic facial expression detection method based on sparse representation plus LBP map

Ouyang, Yuanxin; Sang, Nong; Huang, Rui

doi:10.1016/j.ijleo.2013.05.076

Cited by 17 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike the above work that applied SRC directly on raw image pixels, studies also exploited other feature descriptors. Ouyang et al [2013] suggested using Local Binary Pattern (LBP) maps that generally have good robustness against illumination variations. Fusion of LBP maps and SRC was found to outperform SRC under non-occlusion, occluded eyes, and partial corruption conditions on the CK database.…”

Section: Sparse Representation Approachmentioning

confidence: 99%

“…The training dictionary needs not only sufficient information to effectively represent the test data, but also abundant characteristics to reduce the correlations of training samples from different classes [Ouyang, et al 2013]. To ensure accurate feature extraction, the approaches require precise face location, alignment and normalization, which are done primarily manually in existing work [Cotter 2010a], [Cotter 2010b], [Zhang, et al 2012], [Ouyang, et al 2013]. One important factor in the use of SRC is to choose a proper type of feature descriptor.…”

Section: Sparse Representation Approachmentioning

confidence: 99%

See 1 more Smart Citation

Facial Expression Analysis under Partial Occlusion

et al. 2018

View full text Add to dashboard Cite

Automatic machine-based Facial Expression Analysis (FEA) has made substantial progress in the past few decades driven by its importance for applications in psychology, security, health, entertainment and human computer interaction. The vast majority of completed FEA studies are based on non-occluded faces collected in a controlled laboratory environment. Automatic expression recognition tolerant to partial occlusion remains less understood, particularly in real-world scenarios. In recent years, efforts investigating techniques to handle partial occlusion for FEA have seen an increase. The context is right for a comprehensive perspective of these developments and the state of the art from this perspective. This survey provides such a comprehensive review of recent advances in dataset creation, algorithm development, and investigations of the effects of occlusion critical for robust performance in FEA systems. It outlines existing challenges in overcoming partial occlusion and discusses possible opportunities in advancing the technology. To the best of our knowledge, it is the first FEA survey dedicated to occlusion and aimed at promoting better informed and benchmarked future work.

show abstract

Section: Sparse Representation Approachmentioning

confidence: 99%

Section: Sparse Representation Approachmentioning

confidence: 99%

Facial Expression Analysis under Partial Occlusion

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Sparse representation works well in applications where the original signal y needs to be reconstructed as accurately as possible, such as denoising, image compression, and spectral estimation. Literature [20] successfully used the sparse representation to automatically recognize facial expression. However, for applications like feature selection, it is more important that the representation is discriminative for the given signal classes than a small reconstruction error.…”

Section: Feature Selection For Multivariate Measuresmentioning

confidence: 99%

Feature selection based on sparse representation with the measures of classification error rate and complexity of boundary

Deng

Jin

2015

Optik

View full text Add to dashboard Cite

“…At the first step, features are extracted from images; whereas at the second one, the images are classified into seven groups either by learning methods like neural networks or by classifiers such as K-NN and SVM. Some feature extraction methods, which have been used in the literature, are Gabor features [2][3][4], Eigen faces [5] and LBP features [6][7][8][9][10]. Among all these methods, LBP features seem to be computationally simple, but effective features which are also known as rotation and gray scale invariant texture descriptors [11].…”

Section: Introductionmentioning

confidence: 99%

“…Later, they have enhanced their experimental results in [9] by applying their proposed approach on various datasets, and also using several classifiers and learning methods. Moreover, Ouyang et al in [10] have made use of LBP texture feature to produce an LBP map and besides, they utilized sparse representation based classification (SRC) method for facial expression recognition.…”

Section: Introductionmentioning

confidence: 99%

Facial expression recognition using high order directional derivative local binary patterns

Tabatabaei

Chalechale

Moghimi

2015

2015 2nd International Conference on Pattern Recognition and Image Analysis (IPRIA)

View full text Add to dashboard Cite

The most expressive manner which human can reveal his emotional states is facial expression. Automatic facial expression recognition is an emerging field of study having extensive applications among which the human-computer interaction (HCI) has received lots of attentions in recent years. The features extracted from facial images, in order to recognize facial expressions, play an essential role in effectiveness of the facial image descriptors. Local binary pattern (LBP) texture descriptors have been known as simple, yet efficient descriptors which are noticeably used for extracting facial patterns from images. Recently, a generalized form of local binary pattern has been introduced which can offer a more precise image description than simple LBP descriptors. Consequently, it would be expected that taking the advantage of using these new LBP texture descriptors will produce more promising results in comparison with use of simple local binary pattern descriptors. In this paper, a novel method has been proposed for image feature extraction using these new image texture descriptors (generalized LBP); then, the obtained results have been compared to the results produced when applying simple LBP descriptors. Furthermore, K-NN and SVM have been used as classifiers in the proposed approach. Finally, a comparison between the proposed method and the existing local binary pattern algorithms for facial expression recognition concludes the superiority of the proposed algorithm over its existing counterparts. Keywords-derivative local binary patterns, facial expression recognition, support vector machine.

show abstract

Robust automatic facial expression detection method based on sparse representation plus LBP map

Cited by 17 publications

References 24 publications

Facial Expression Analysis under Partial Occlusion

Facial Expression Analysis under Partial Occlusion

Feature selection based on sparse representation with the measures of classification error rate and complexity of boundary

Facial expression recognition using high order directional derivative local binary patterns

Contact Info

Product

Resources

About