Collaborative expression representation using peak expression and intra class variation face images for practical subject-independent emotion recognition in videos

Lee, Seol‐Hoon; Baddar, Wissam J.; Ro, Yong Man

doi:10.1016/j.patcog.2015.12.016

Cited by 48 publications

(17 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is interesting to observe that the proposed descriptor achieves better accuracy than other edgebased descriptors including LDP, LDN, LPTP, and PTP and ties with LBP. Nevertheless, LDSP works better than LBP, LPQ, and Gabor when they are applied with SRC [29]. Moreover, the best result reported in [29] is slightly better than the proposed method.…”

Section: Resultsmentioning

confidence: 80%

“…We present the comparative results in Table 2, where we observe that LDSP achieves higher accuracy than other descriptors, such as, LBP, LDP, LDN, LPTP, and PTP, for 7-class recognition. Lee et al [29] presented some of the descriptors' results, including LBP, LPQ, and Gabor with sparse representation classifier (SRC), which were also found inferior to the proposed descriptor. Nevertheless, we compare our results against other state-of-the-art methods [25,[29][30][31][32].…”

Section: Ck+ Resultsmentioning

confidence: 99%

“…Lee et al [29] presented some of the descriptors' results, including LBP, LPQ, and Gabor with sparse representation classifier (SRC), which were also found inferior to the proposed descriptor. Nevertheless, we compare our results against other state-of-the-art methods [25,[29][30][31][32]. Among these methods, Lucey et al [25] reported several sparse methods using geometric information of the facial components, namely similarity-normalized shape (SPTS), canonical appearance features (CAPP), and their combination (SPTS + CAPP).…”

Section: Ck+ Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Local directional-structural pattern for person-independent facial expression recognition

Makhmudkhujaev¹,

Iqbal²,

Ryu³

et al. 2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Existing popular descriptors for facial expression recognition often suffer from inconsistent feature description, experiencing poor accuracies. We present a new local descriptor, local directional-structural pattern (LDSP), in this work to address this issue. Unlike the existing local descriptors using only the texture or edge information to represent the local structure of a pixel, the proposed LDSP utilizes the positional relationship of the top edge responses of the target pixel to extract more detailed structural information of the local texture. We further exploit such information to characterize expression-affiliated crucial textures while discarding the random noisy patterns. Moreover, we introduce a globally adaptive thresholding strategy to exclude futile flat patterns. Hence, LDSP offers a stable description of facial expressions with the explicit representation of the expression-affiliated features along with the exclusion of random futile textures. We visualize the efficacy of the proposed method in three folds. First, the LDSP descriptor possesses a moderate code-length owing to the exclusion of the futile patterns, yielding less computation time than other edge descriptors. Second, for person-independent expression recognition in benchmark datasets, LDSP demonstrates higher accuracy than existing descriptors and other state-of-the-art methods. Third, LDSP shows better performance than other descriptors against noise and low resolution, exhibiting its robustness under such uneven conditions.

show abstract

Section: Resultsmentioning

confidence: 80%

Section: Ck+ Resultsmentioning

confidence: 99%

Section: Ck+ Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Local directional-structural pattern for person-independent facial expression recognition

Makhmudkhujaev¹,

Iqbal²,

Ryu³

et al. 2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…Among the appearance-based methods, we considered LBP, LDP, LDN, PTP, HOG, LPQ, Gabor, and LDTP. Furthermore, we compared against a method that uses a manifold based sparse representation (MSR) [20] and approaches dealing with intra-class variations [21], [22]. It is important to note that we compared our results against some recent deep methods, including GoogLeNet [23], AlexNet [23], and the proposed network in [23].…”

Section: Performance Under Positional Variation (Misalignment)mentioning

confidence: 99%

Person-Independent Facial Expression Recognition with Histograms of Prominent Edge Directions

2018

KSII TIIS

View full text Add to dashboard Cite

This paper presents a new descriptor, named Histograms of Prominent Edge Directions (HPED), for the recognition of facial expressions in a person-independent environment. In this paper, we raise the issue of sampling error in generating the code-histogram from spatial regions of the face image, as observed in the existing descriptors. HPED describes facial appearance changes based on the statistical distribution of the top two prominent edge directions (i.e., primary and secondary direction) captured over small spatial regions of the face. Compared to existing descriptors, HPED uses a smaller number of code-bins to describe the spatial regions, which helps avoid sampling error despite having fewer samples while preserving the valuable spatial information. In contrast to the existing Histogram of Oriented Gradients (HOG) that uses the histogram of the primary edge direction (i.e., gradient orientation) only, we additionally consider the histogram of the secondary edge direction, which provides more meaningful shape information related to the local texture. Experiments on popular facial expression datasets demonstrate the superior performance of the proposed HPED against existing descriptors in a person-independent environment.

show abstract

“…Facial expression recognition (FER) has attracted much attention and played an important role in human emotions due to its wide applications [1][2][3][4]. Moreover, FER relates to pattern recognition, image processing, computer vision, and other aspects [5].…”

Section: Introductionmentioning

confidence: 99%

Adaptive joint block-weighted collaborative representation for facial expression recognition

Sun¹,

Hu²,

Wang³

et al. 2017

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Collaborative expression representation using peak expression and intra class variation face images for practical subject-independent emotion recognition in videos

Cited by 48 publications

References 61 publications

Local directional-structural pattern for person-independent facial expression recognition

Local directional-structural pattern for person-independent facial expression recognition

Person-Independent Facial Expression Recognition with Histograms of Prominent Edge Directions

Adaptive joint block-weighted collaborative representation for facial expression recognition

Contact Info

Product

Resources

About