Improvement of Eye Tracking Based on Deep Learning Model for General Purpose Applications
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 extrao...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Al-Nahrain Journal for Engineering Sciences
2022-04-01
|
| Series: | مجلة النهرين للعلوم الهندسية |
| Subjects: | |
| Online Access: | https://nahje.com/index.php/main/article/view/918 |
| _version_ | 1828913147301330944 |
|---|---|
| author | Ahmed Aamer Almindelawy Mohammed H. Ali |
| author_facet | Ahmed Aamer Almindelawy Mohammed H. Ali |
| author_sort | Ahmed Aamer Almindelawy |
| collection | DOAJ |
| description |
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.
|
| first_indexed | 2024-12-13T19:32:07Z |
| format | Article |
| id | doaj.art-5cb20e1dfd8a451ebbd9a51a5aa6f6d8 |
| institution | Directory Open Access Journal |
| issn | 2521-9154 2521-9162 |
| language | English |
| last_indexed | 2024-12-13T19:32:07Z |
| publishDate | 2022-04-01 |
| publisher | Al-Nahrain Journal for Engineering Sciences |
| record_format | Article |
| series | مجلة النهرين للعلوم الهندسية |
| spelling | doaj.art-5cb20e1dfd8a451ebbd9a51a5aa6f6d82022-12-21T23:33:54ZengAl-Nahrain Journal for Engineering Sciencesمجلة النهرين للعلوم الهندسية2521-91542521-91622022-04-0125110.29194/NJES.25010012Improvement of Eye Tracking Based on Deep Learning Model for General Purpose ApplicationsAhmed Aamer Almindelawy0Mohammed H. Ali1College of Engineering, Al-Nahrain UniversityCollege of Engineering, Al-Nahrain University 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. https://nahje.com/index.php/main/article/view/918Eye TrackingArtificial IntelligenceMachine LearningDeep LearningCNN |
| spellingShingle | Ahmed Aamer Almindelawy Mohammed H. Ali Improvement of Eye Tracking Based on Deep Learning Model for General Purpose Applications مجلة النهرين للعلوم الهندسية Eye Tracking Artificial Intelligence Machine Learning Deep Learning CNN |
| title | Improvement of Eye Tracking Based on Deep Learning Model for General Purpose Applications |
| title_full | Improvement of Eye Tracking Based on Deep Learning Model for General Purpose Applications |
| title_fullStr | Improvement of Eye Tracking Based on Deep Learning Model for General Purpose Applications |
| title_full_unstemmed | Improvement of Eye Tracking Based on Deep Learning Model for General Purpose Applications |
| title_short | Improvement of Eye Tracking Based on Deep Learning Model for General Purpose Applications |
| title_sort | improvement of eye tracking based on deep learning model for general purpose applications |
| topic | Eye Tracking Artificial Intelligence Machine Learning Deep Learning CNN |
| url | https://nahje.com/index.php/main/article/view/918 |
| work_keys_str_mv | AT ahmedaameralmindelawy improvementofeyetrackingbasedondeeplearningmodelforgeneralpurposeapplications AT mohammedhali improvementofeyetrackingbasedondeeplearningmodelforgeneralpurposeapplications |