A hybrid feature descriptor with Jaya optimised least squares SVM for facial expression recognition

Abstract

Facial expression recognition has been a long‐standing problem in the field of computer vision. This paper proposes a new simple scheme for effective recognition of facial expressions based on a hybrid feature descriptor and an improved classifier. Inspired by the success of stationary wavelet transform in many computer vision tasks, stationary wavelet transform is first employed on the pre‐processed face image. The pyramid of histograms of orientation gradient features is then computed from the low‐frequency stationary wavelet transform coefficients to capture more prominent details from facial images. The key idea of this hybrid feature descriptor is to exploit both spatial and frequency domain features which at the same time are robust against illumination and noise. The relevant features are subsequently determined using linear discriminant analysis. A new least squares support vector machine parameter tuning strategy is proposed using a contemporary optimisation technique called Jaya optimisation for classification of facial expressions. Experimental evaluations are performed on Japanese female facial expression and the Extended Cohn–Kanade (CK+) datasets, and the results based on 5‐fold stratified cross‐validation test confirm the superiority of the proposed method over state‐of‐the‐art approaches.

Hand Function Rehabilitation Training Robot Based on Ycbcr and CNN

“…This fully utilizes the fact that the human eye is more sensitive to brightness changes and relatively less sensitive to color changes. Therefore, the study adopts the Ycbcr color space method to extract images of gesture skin regions [17]. Although Ycbcr is not an absolute color space, it is a method of encoding RGB information.…”

Facial expression recognition based on improved residual network

“…Using DCNN features, Mayya et al [18] proposed a new method for automated facial expression recognition. Kar et al [19] proposed a new simple and effective facial expression recognition method based on mixed feature descriptors and improved classifiers. In a new deep learning framework presented by Rajan et al [20], convolutional neural network (CNN) is combined with longterm and short-term memory (LSTM) units for real-time facial expression recognition.…”

“…Kar et al. [19] proposed a new simple and effective facial expression recognition method based on mixed feature descriptors and improved classifiers. In a new deep learning framework presented by Rajan et al.…”

Small insulator target detection based on multi‐feature fusion

“…SVM is a supervised learning method in the field of machine learning. In the past 20 years, it is one of the most influential machine learning algorithms [25–27]. Equation () shows the original problem of SVM: $$$$\begin{equation}\left\{ { \def\eqcellsep{&}\begin{array}{@{}*{1}{c}@{}} {\mathop {{\rm{max}}}\limits_{\omega ,b} \mathop {\min }\limits_{{x}_i} \dfrac{{\left| {{\omega }^T{x}_i + b} \right|}}{{\left\| \omega \right\|}}}\\[9pt] {{y}_i({\omega }^T{x}_i + b) > 0} \end{array} } \right.\end{equation}$$$$where $${w}^Tx + b$$ represents the hyper‐plane, y i is the sample label value, y i = 1 when the sample is positive and y i = −1 when the sample is negative.…”

“…SVM is a supervised learning method in the field of machine learning. In the past 20 years, it is one of the most influential machine learning algorithms [25][26][27]. Equation (15) shows the original problem of SVM: In practice, SVM optimizes the classification problem by error penalty factor C and kernel function, as shown in Equation (16).…”