Efficient facial expression recognition using histogram of oriented gradients in wavelet domain

Nigam, Swati; Singh, Rajiv; Misra, A. K.

doi:10.1007/s11042-018-6040-3

Cited by 72 publications

(22 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ghimire et al divided the whole face region into domain-specific local regions; then region-specific appearance features and geometric features are extracted from the domain-specific regions for facial expression recognition [ 22 ]. Nigam et al retrieved Histogram of Oriented Gradients (HOG) feature in DWT domain and an SVM was used for expression recognition [ 23 ]. Kamarol et al proposed spatiotemporal texture map (STTM) to capture subtle spatial and temporal variations of facial expressions with low computational complexity.…”

Section: Related Workmentioning

confidence: 99%

Facial Expression Recognition with LBP and ORB Features

Niu

Gao

Guo

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Emotion plays an important role in communication. For human–computer interaction, facial expression recognition has become an indispensable part. Recently, deep neural networks (DNNs) are widely used in this field and they overcome the limitations of conventional approaches. However, application of DNNs is very limited due to excessive hardware specifications requirement. Considering low hardware specifications used in real-life conditions, to gain better results without DNNs, in this paper, we propose an algorithm with the combination of the oriented FAST and rotated BRIEF (ORB) features and Local Binary Patterns (LBP) features extracted from facial expression. First of all, every image is passed through face detection algorithm to extract more effective features. Second, in order to increase computational speed, the ORB and LBP features are extracted from the face region; specifically, region division is innovatively employed in the traditional ORB to avoid the concentration of the features. The features are invariant to scale and grayscale as well as rotation changes. Finally, the combined features are classified by Support Vector Machine (SVM). The proposed method is evaluated on several challenging databases such as Cohn-Kanade database (CK+), Japanese Female Facial Expressions database (JAFFE), and MMI database; experimental results of seven emotion state (neutral, joy, sadness, surprise, anger, fear, and disgust) show that the proposed framework is effective and accurate.

show abstract

Section: Related Workmentioning

confidence: 99%

Facial Expression Recognition with LBP and ORB Features

Niu

Gao

Guo

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Wang et al [35] fused HOG features with Weber local descriptor and classified facial expressions using chi-square distance with nearest neighbour technique. Nigam et al [36] computed HOG features in discrete wavelet domain for effective characterization of facial expressions. Zeng et al [37] presented a novel deep architecture wherein they extracted from emotional images HOG features and concatenated them with local binary pattern and grey levels and learnt the discriminative high dimensional features using sparse auto-encoders.…”

Section: Hog and Facial Expression Classificationmentioning

confidence: 99%

Dynamic Features Based on Flow-Correlation and HOG for Recognition of Discrete Facial Expressions

Anthwal¹,

Ganotra²

2020

RIA

View full text Add to dashboard Cite

Facial expressions are the most preeminent means of conveying one’s emotions and play a significant role in interpersonal communication. Researchers are in pursuit of endowing machines with the ability to interpret emotions from facial expressions as that will make human-computer interaction more efficient. With the objective of effective affect cognition from visual information, we present two dynamic descriptors that can recognise seven principal emotions. The variables of the appearance-based descriptor, FlowCorr, indicate intra-class similarity and inter-class difference by quantifying the degree of correlation of optical flow associated with the image pair and each pre-designed template describing the motion pattern associated with different expressions. The second shape-based descriptor, dyn-HOG, finds the HOG values of the difference image derived by subtracting neutral face from emotional face, and is demonstrated to be more discriminative than previously used static HOG descriptors for classifying facial expressions. Recognition accuracies with multi-class support vector machine obtained on the CK+ and KDEF-dyn datasets are competent with the results of state-of-the-art techniques and empirical analysis of human cognition of emotions.

show abstract

“…Commonly, researchers try to construct some intermediate features to represent different view characters of same image or object, classical methods commonly used by them include the structured and repetitive visual unit, key points and local descriptors, etc [7]- [9]. Such as local binary patterns (LBP) [10], local extrema patterns (LEP) [11], histogram of oriented gradients (HOG) [12], multi-trend structure descriptor (MTSD) [13], pyramid histogram of oriented gradients (PHOG) [14], scale-invariant feature transform (SIFT) [15] and Gist [16]. Most of these methods try to extract multiple views features of image for retrieval and classification to increase the system's final accuracy.…”

Section: Introductionmentioning

confidence: 99%

A Multi-View Fusion Method via Tensor Learning and Gradient Descent for Image Features

Zhang

Liu

et al. 2021

IEEE Access

View full text Add to dashboard Cite

In many computer vision applications, one image can be represented by multiple heterogeneous features from different views, most of them commonly locate in high-dimensional space. These features can reflect different characteristics of one same object, they contain compatible and complementary information among each other. How to construct an uniform low-dimensional embedding features which represent useful information of multi-view features is still an important and urgent issue to be solved. Therefore, we propose a multi-view fusion method via tensor learning and gradient descent (MvF-TG) in this paper. MvF-TG reconstructs a low dimensional mapping subspace of each object by utilizing its k nearest neighbors, which preserves the underlying neighborhood structure of the original local manifold. The new method can effectively exploit the spatial correlation information from the multi-view features by tensor learning. Furthermore, the method constructs a gradient descent optimization model to generate the better unified low dimensional embedding. The proposed method is compared with several single-view and multi-view dimensional reduction methods in these indicators of P, R, MAP and F-measure. In the retrieval experiments, the P values of the new method respectively are 86.80%, 52.00%, 68.56% and 78.80% on datasets of Corel1k, Corel5k, Corel10k and Holidays. In the classification experiments, the mean accuracies of it respectively are 47.94% and 87.58% on datasets of Caltech101 and Coil. These values are higher than those obtained by other comparison methods, various evaluations based on the applications of image classification and retrieval demonstrate the effectiveness of our proposed method on multi-view feature fusion dimension reduction.

show abstract

Efficient facial expression recognition using histogram of oriented gradients in wavelet domain

Cited by 72 publications

References 51 publications

Facial Expression Recognition with LBP and ORB Features

Facial Expression Recognition with LBP and ORB Features

Dynamic Features Based on Flow-Correlation and HOG for Recognition of Discrete Facial Expressions

A Multi-View Fusion Method via Tensor Learning and Gradient Descent for Image Features

Contact Info

Product

Resources

About