Eye state recognition based on deep integrated neural network and transfer learning

Zhao, Lei; Wang, Zengcai; Zhang, Guoxin; Qi, Yazhou; Wang, Xiaojin

doi:10.1007/s11042-017-5380-8

Cited by 46 publications

(28 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, a transfer learning strategy is applied to overcome the dataset shortage. This method tested on three datasets and reported 97.20% accuracy on the ZJU dataset with their DINN network [21]. Another research tried to find the landmark points to find the Eye Aspect Ratio (EAR) and Eye Closure Ratio (ECR) as a sign of drowsiness [22].…”

Section: Related Workmentioning

confidence: 99%

“…Hence, this network can learn more elaborate features. In terms of comparing FD-NN to Zhao [21], and TL-VGG19, TL-VGG16 it worth mentioning that there is a relationship between the number of parameters that the network needs to learn and the size of the dataset. As much as the number of hidden layer increase, the network needs greater dataset.…”

Section: Accuracy Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Driver Safety Development: Real-Time Driver Drowsiness Detection System Based on Convolutional Neural Network

2020

View full text Add to dashboard Cite

This paper focuses on the challenge of driver safety on the road and presents a novel system for driver drowsiness detection. In this system, to detect the falling sleep state of the driver as the sign of drowsiness, Convolutional Neural Networks (CNN) are used with regarding the two goals of real-time application, including high accuracy and fastness. Three networks introduced as a potential network for eye status classification in which one of them is a Fully Designed Neural Network (FD-NN) and others use Transfer Learning in VGG16 and VGG19 with extra designed layers (TL-VGG). Lack of an available and accurate eye dataset strongly feels in the area of eye closure detection. Therefore, a new comprehensive dataset proposed. The experimental results show the high accuracy and low computational complexity of the eye closure estimation and the ability of the proposed framework on drowsiness detection.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Accuracy Evaluationmentioning

confidence: 99%

Driver Safety Development: Real-Time Driver Drowsiness Detection System Based on Convolutional Neural Network

2020

View full text Add to dashboard Cite

show abstract

“…Human eye information is crucial to gain deeper understanding of one's physiological and psychological conditions, thus, finding its applications in the domains like facial recognition, medical diagnosis, facial expression recognition, auxiliary driving, drowsiness detection and psychological analysis. This emphasizes the need for an accurate and efficient eye detector [33] [34] [35]. The main aim of this line of research is to extract eye components and its characteristics like the iris, pupil, eyelids along with its geometric shape [36].…”

Section: Eyes Analysismentioning

confidence: 99%

“…However, deep learning methods like deep neural networks and deep convolutional neural network have proven to work better in analyzing eyes even in noisy conditions. Facial area in the image is localized using Viola-Jones face detector [33] [35] and then segmented using AdaBoost algorithm [33]. Eye patches are extracted from facial regions which are then fed to the neural network [35].…”

Section: Vatamentioning

confidence: 99%

“…Facial area in the image is localized using Viola-Jones face detector [33] [35] and then segmented using AdaBoost algorithm [33]. Eye patches are extracted from facial regions which are then fed to the neural network [35]. Few approaches also involve localization of iris center of the eyes considering the circularity score by taking into account the symmetry of pixels at radius [33].…”

Section: Vatamentioning

confidence: 99%

See 1 more Smart Citation

Classification of Humans into Ayurvedic Prakruti Types using Computer Vision

Gadre

View full text Add to dashboard Cite

Ayurveda, a 5000 years old Indian medical science, believes that the universe and hence humans are made up of five elements namely ether, fire, water, earth, and air. The three Doshas (Tridosha) Vata, Pitta, and Kapha originated from the combinations of these elements. Every person has a unique combination of Tridosha elements contributing to a person's 'Prakruti'. Prakruti governs the physiological and psychological tendencies in all living beings as well as the way they interact with the environment. This balance influences their physiological features like the texture and colour of skin, hair, eyes, length of fingers, the shape of the palm, body frame, strength of digestion and many more as well as the psychological features like their nature (introverted, extroverted, calm, excitable, intense, laidback), and their reaction to stress and diseases. All these features are coded in the constituents at the time of a person's creation and do not change throughout their lifetime. Ayurvedic doctors analyze the Prakruti of a person either by assessing the physical features manually and/or by examining the nature of their heartbeat (pulse). Based on this analysis, they diagnose, prevent and cure the disease in patients by prescribing precision medicine. This project focuses on identifying Prakruti of a person by analysing his facial features like hair, eyes, nose, lips and skin colour using facial recognition techniques in computer vision. This is the first of its kind research in this problem area that attempts to bring image processing into the domain of Ayurveda.

show abstract

A Simulation Optimization of Research and Study Travel Route Based on Transfer Learning and Clustering Algorithm

2022

Cyber Security Intelligence and Analytics

View full text Add to dashboard Cite

Eye state recognition based on deep integrated neural network and transfer learning

Cited by 46 publications

References 50 publications

Driver Safety Development: Real-Time Driver Drowsiness Detection System Based on Convolutional Neural Network

Driver Safety Development: Real-Time Driver Drowsiness Detection System Based on Convolutional Neural Network

Classification of Humans into Ayurvedic Prakruti Types using Computer Vision

A Simulation Optimization of Research and Study Travel Route Based on Transfer Learning and Clustering Algorithm

Contact Info

Product

Resources

About