Face expression recognition based on NGO-BILSTM model

Abstract

IntroductionFacial expression recognition has always been a hot topic in computer vision and artificial intelligence. In recent years, deep learning models have achieved good results in accurately recognizing facial expressions. BILSTM network is such a model. However, the BILSTM network's performance depends largely on its hyperparameters, which is a challenge for optimization.MethodsIn this paper, a Northern Goshawk optimization (NGO) algorithm is proposed to optimize the hyperparameters of BILSTM network for facial expression recognition. The proposed methods were evaluated and compared with other methods on the FER2013, FERplus and RAF-DB datasets, taking into account factors such as cultural background, race and gender.ResultsThe results show that the recognition accuracy of the model on FER2013 and FERPlus data sets is much higher than that of the traditional VGG16 network. The recognition accuracy is 89.72% on the RAF-DB dataset, which is 5.45, 9.63, 7.36, and 3.18% higher than that of the proposed facial expression recognition algorithms DLP-CNN, gACNN, pACNN, and LDL-ALSG in recent 2 years, respectively.DiscussionIn conclusion, NGO algorithm effectively optimized the hyperparameters of BILSTM network, improved the performance of facial expression recognition, and provided a new method for the hyperparameter optimization of BILSTM network for facial expression recognition.

Enhancing Facial Expression Recognition System in Online Learning Context Using Efficient Deep Learning Model

“…To gauge the model's resilience, we initially compared its performance to FER-2013. Our model outperformed the models of Arriaga et al [35], J. Li et al [36], Subramanian et al [37], Borgalli et al [38], Kunyoung Lee [20], Jiarui Zhong [21], and Hongmei Zhong [23], achieving accuracy improvements of 22.13%, 16.13%, 0.11%, 1.33%, 14.53%, 36.84%, and 11.33%, respectively. We also evaluated the resilience of our model using the CK+ dataset, where it demonstrated a noteworthy performance compared to state-of-the-art methods.…”

“…In the research conducted by Jiarui Zhong et al [21], the authors employed a Northern Goshawk optimization (NGO) algorithm to fine-tune the hyperparameters of the BILSTM network, specifically for the task of facial expression recognition. Their proposed methodologies underwent thorough evaluation and comparison with other existing approaches across multiple datasets, including FER2013, FERplus, and RAF-DB, while considering factors such as cultural background, race, and gender.…”

Revolutionizing online education: Advanced facial expression recognition for real-time student progress tracking via deep learning model

“…Initially, we evaluated the model's performance against FER-2013 to measure its resilience. Our proposed model demonstrated superior performance compared to models labeled as [34,[58][59][60][61][62][63][64], and [3], achieving accuracy improvements of 25 73.00% [3] 73.40% [56] 70.00% [57] 64.70% Model in this paper 91.71%…”