Gaze Tracking Using an Unmodified Web Camera and Convolutional Neural Network

Ansari, Mohd Faizan; Kasprowski, Paweł; Obetkal, Marcin

doi:10.3390/app11199068

Cited by 16 publications

(8 citation statements)

References 38 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2021, Mohd Faizan Ansari, Pawel Kasprowski, and Marcin Obetkal presented in an Article titled "Gaze tracking using an unmodified web camera and convolutional neural network", a gaze estimation using a CNN that can be applied under various circumstances and platforms without additional special hardware requirements. It made an approve that Gaze estimation is possible with acceptable accuracy [14]. This paper is the basis of the comparison mentioned later.…”

Section: Related Workmentioning

confidence: 92%

Improvement of Eye Tracking Based on Deep Learning Model for General Purpose Applications

Almindelawy

Ali

2022

NJES

View full text Add to dashboard Cite

The interest in the Eye-tracking technology field dramatically grew up in the last two decades for different purposes and applications like keeping the focus of where the person is looking, how his pupils and irises are reacting for a variety of actions, etc. The resulted data can deliver an extraordinary amount of information about the user when it's interlocked through advanced data analysis systems, it may show information concerned with the user’s age, gender, biometric identity, interests, etc. This paper is concerned about eye motion tracking as an unadulterated tool for different applications in any field required. The improvements in this area of artificial intelligence (AI), machine learning (ML), and deep learning (DL) with eye-tracking techniques allow large opportunities to develop algorithms and applications. In this paper number of models were proposed based on Convolutional neural network (CNN) have been designed, and then the most powerful and accurate model was chosen. The dataset used for the training process (for 16 screen points) consists of 2800 training images and 800 test images (with an average of 175 training images and 50 test images for each spot on the screen of the 16 spots), and it can be collected by the user of any application based on this model. The highest accuracy achieved by the best model was (91.25%) and the minimum loss was (0.23%). The best model consists of (11) layers (4 convolutions, 4 Max pooling, and 3 Dense). Python 3.7 was used to implement the algorithms, KERAS framework for the deep learning algorithms, Visual studio code as an Integrated Development Environment (IDE), and Anaconda navigator for downloading the different libraries. The model was trained with data that can be gathered using cameras of laptops or PCs and without the necessity of special and expensive equipment, also It can be trained for any single eye, depending on application requirements.

show abstract

Section: Related Workmentioning

confidence: 92%

Improvement of Eye Tracking Based on Deep Learning Model for General Purpose Applications

Almindelawy

Ali

2022

NJES

View full text Add to dashboard Cite

show abstract

“…These methods typically explore anatomical features of the human eyes such as the pupil center, iris edge, and corneal reflections. By analyzing these features, they determine a set of unique eye characteristics, which are essential for accurate gaze prediction [17]. However, these methods often require specialized equipment like high-resolution cameras or infrared sensors and can be sensitive to external factors such as lighting and user head movements.…”

Section: Introductionmentioning

confidence: 99%

Gaze-Swin: Enhancing Gaze Estimation with a Hybrid CNN-Transformer Network and Dropkey Mechanism

Zhao,

Wang,

Luo

et al. 2024

Electronics

View full text Add to dashboard Cite

Gaze estimation, which seeks to reveal where a person is looking, provides a crucial clue for understanding human intentions and behaviors. Recently, Visual Transformer has achieved promising results in gaze estimation. However, dividing facial images into patches compromises the integrity of the image structure, which limits the inference performance. To tackle this challenge, we present Gaze-Swin, an end-to-end gaze estimation model formed with a dual-branch CNN-Transformer architecture. In Gaze-Swin, we adopt the Swin Transformer as the backbone network due to its effectiveness in handling long-range dependencies and extracting global features. Additionally, we incorporate a convolutional neural network as an auxiliary branch to capture local facial features and intricate texture details. To further enhance robustness and address overfitting issues in gaze estimation, we replace the original self-attention in the Transformer branch with Dropkey Assisted Attention (DA-Attention). In particular, this DA-Attention treats keys in the Transformer block as Dropout units and employs a decay Dropout rate schedule to preserve crucial gaze representations in deeper layers. Comprehensive experiments on three benchmark datasets demonstrate the superior performance of our method in comparison to the state of the art.

show abstract

“…Recently, many studies have been carried out to develop a method of tracking saccadic eye movements outside of the clinical environment via smartphone cameras and surveillance devices ( Lai et al, 2020 ; Ansari, Kasprowski & Obetkal, 2021 ). Appearance-based gaze estimation with the help of convolutional neural networks was found to be successful in accurately decoding saccadic eye movements from facial images and desktop cameras ( Ansari, Kasprowski & Obetkal, 2021 ). This model advances the mental fatigue detection method via saccades as it allows for individuals to be tested for mental fatigue whilst they carry out their day-to-day living.…”

Section: Introductionmentioning

confidence: 99%

Understanding mental fatigue and its detection: a comparative analysis of assessments and tools

Kunasegaran,

Ismail,

Ramasamy

et al. 2023

PeerJ

View full text Add to dashboard Cite

Mental fatigue has shown to be one of the root causes of decreased productivity and overall cognitive performance, by decreasing an individual’s ability to inhibit responses, process information and concentrate. The effects of mental fatigue have led to occupational errors and motorway accidents. Early detection of mental fatigue can prevent the escalation of symptoms that may lead to chronic fatigue syndrome and other disorders. To date, in clinical settings, the assessment of mental fatigue and stress is done through self-reported questionnaires. The validity of these questionnaires is questionable, as they are highly subjective measurement tools and are not immune to response biases. This review examines the wider presence of mental fatigue in the general population and critically compares its various detection techniques (i.e., self-reporting questionnaires, heart rate variability, salivary cortisol levels, electroencephalogram, and saccadic eye movements). The ability of these detection tools to assess inhibition responses (which are sensitive enough to be manifested in a fatigue state) is specifically evaluated for a reliable marker in identifying mentally fatigued individuals. In laboratory settings, antisaccade tasks have been long used to assess inhibitory control and this technique can potentially serve as the most promising assessment tool to objectively detect mental fatigue. However, more studies need to be conducted in the future to validate and correlate this assessment with other existing measures of mental fatigue detection. This review is intended for, but not limited to, mental health professionals, digital health scientists, vision researchers, and behavioral scientists.

show abstract

Gaze Tracking Using an Unmodified Web Camera and Convolutional Neural Network

Cited by 16 publications

References 38 publications

Improvement of Eye Tracking Based on Deep Learning Model for General Purpose Applications

Improvement of Eye Tracking Based on Deep Learning Model for General Purpose Applications

Gaze-Swin: Enhancing Gaze Estimation with a Hybrid CNN-Transformer Network and Dropkey Mechanism

Understanding mental fatigue and its detection: a comparative analysis of assessments and tools

Contact Info

Product

Resources

About