Real-time eye state recognition using dual convolutional neural network ensemble

Saurav, Sumeet; Gidde, Prashant Sadashiv; Saini, Ramesh Kumar; Singh, Sanjay

doi:10.1007/s11554-022-01211-5

Cited by 10 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the performance comparison of DFNN with the proposed method on the ZJU dataset, the proposed method outperformed DFNN in both accuracy and AUC metric. In CEW dataset, Saurav et al [28] and Liu et al [26] are the closest to the accuracy of the proposed method. As a result of the comparative analysis of the proposed method on the CEW dataset, it is seen that it has achieved superior performance than in previous studies.…”

Section: Real-world Scenario Testing Of the Proposed Methodsmentioning

confidence: 90%

“…In the compared performance metrics, the DCNN method has shown that it is one of the most successful methods in AUC performance metric for eye state recognition compared to previous studies. As for the accuracy metric, the DCNNE suggested by Sauraw et al [28] has the highest accuracy, but the AUC metric was not presented. Therefore, it has been observed that the proposed method has the highest success in comparing the state-ofthe-art methods in the literature with both AUC and accuracy metrics presented together.…”

Section: Real-world Scenario Testing Of the Proposed Methodsmentioning

confidence: 99%

“…As a result, they performed these operations on the ZJU dataset and stated that among the classification models the automatic encoder model based on the HOG feature achieved the best performance. Saurav et al [28] proposed a vision-based system for real-time eye state recognition on an embedded platform. In this proposed system, to overcome the overfitting problem created by deep neural networks in small datasets, a dual convolution neural network ensemble (DCNNE) model is developed by combining two lightweight CNNs based on transfer learning-based fine-tuning.…”

Section: Cnnmentioning

confidence: 99%

“…Because of the superior performance of CNN in image classification, one of the sub-branches of machine learning has displayed a considerable effect in many imagebased applications [17]. As a consequence, in research by Liu et al [26], Huang et al [10], Saurav et al [28] and Liang et al [29], deep learning-based CNN approaches, have gotten started to be preferred in eye state recognition. Unlike other machine learning approaches, CNN's multi-layered structure does not demand meticulous engineering or knowledge because it yields representational learning from its raw data.…”

Section: Cnnmentioning

confidence: 99%

See 3 more Smart Citations

An Eye State Recognition System Using Transfer Learning: AlexNet-Based Deep Convolutional Neural Network

Kayadibi

Güraksın

Ergün

et al. 2022

Int J Comput Intell Syst

View full text Add to dashboard Cite

For eye state recognition (closed or open), a mechanism based on deep convolutional neural network (DCNN) using the Zhejiang University (ZJU) and Closed Eyes in the Wild (CEW) dataset, has been proposed in this paper. In instances where blinking is consequential, eye state recognition plays a critical part for the development of human–machine interaction (HMI) solutions. To accomplish this objective, pre-trained CNN architectures on ImageNet were first trained on the both dataset, which included both open and closed-eye states, and then they were tested, and their performance was quantified. The AlexNet design has proven to be more successful owing to these assessments. The ZJU and CEW datasets were leveraged to train the DCNN architecture, which was constructed employing AlexNet modifications for performance enhancement. On the both datasets, the suggested DCNN architecture was tested for performance. The achieved DCNN design was found to have 97.32% accuracy, 95.37% sensitivity, 97.97% specificity, 93.99% precision, 94.67% F1 score, and 99.37% AUC values in the ZJU dataset, while it was found to have 97.93% accuracy, 98.74% sensitivity, 97.15% specificity, 97.11% precision, 97.92% F1 score, and 99.69% AUC values in the CEW dataset. Accordingly, when compared to CNN architectures, it scored the maximum performance. At the same time, the DCNN architecture proposed on the ZJU and CEW datasets has been confirmed to be an acceptable and productive solution for eye state recognition depending on the outcomes compared to the studies in the literature. This method may contribute to the development of HMI systems by adding to the literature on eye state recognition.

show abstract

Section: Real-world Scenario Testing Of the Proposed Methodsmentioning

confidence: 90%

Section: Real-world Scenario Testing Of the Proposed Methodsmentioning

confidence: 99%

Section: Cnnmentioning

confidence: 99%