DIVE Medical S.L. built the DIVE MTurk Camera Eye Tracking as a Free app. This SERVICE is provided by DIVE Medical S.L. at no cost and is intented for use as is.
This page is used to inform visitors regarding our policies with the collection, use, and disclosure of Personal Information if anyone decided to use our Service.
1. DIVE MTurk Camera Eye Tracking app
This application is part of a research project that we are carrying out at DIVE Medical S.L. You can participate via Amazon Mechanical Turk HIT “DIVE Camera Eye Tracking.” Your participation is absolutely voluntary, in no case should you feel obliged to participate, but it is important to obtain the knowledge we need. This project has been approved by the Research Ethics Committee of the Autonomous Community of Aragón (Spain). The complete participant information can be found within the application.
This study focuses on investigating the feasibility of new eye tracking systems. An eye tracking system allows to know the point on a digital screen where a user is looking at, based on the collection and analysis of images of the user’s face or eyes. Traditionally, specific eye tracking devices are used for this purpose, which capture infrared images (the entire visible light spectrum is not captured, as in a conventional camera). In these images it is easier to detect the pupils, which is necessary for eye tracking. One of the objectives of this study is to investigate the feasibility of eye tracking systems based on conventional photo or video cameras such as those of any mobile device, tablet or computer, which capture the entire visible light spectrum. For this purpose, different computer techniques (computer vision and artificial intelligence) will be used. The expected result is the verification that it is possible to perform eye tracking with conventional cameras with sufficient accuracy to replace specific eye tracking devices in certain applications, such as the execution of visual tests.
Also, the performance of computer vision techniques or artificial intelligence techniques is conditioned by the quantity and quality of the data used. However, recruitments and real data collection are often costly in time and money. The second objective of this project is to investigate the feasibility of generating synthetic face images from images of real faces, together with the point on the screen where they are looking at. For this purpose, different computer vision and deep learning techniques will be used. The expected result is the verification that it is possible to generate synthetic faces with sufficient quality to improve the performance of the eye tracking system.
As a consequence of this research, the company DIVE Medical S.L. aims to develop an application for mobile devices (tablets, mobiles and/or computers) in which, using the eye tracking techniques with conventional cameras/webcams developed in this study, it is able to carry out visual examinations and the detection of different pathologies through vision. This would improve the visual care of patients, including those who cannot communicate verbally.
2. Data to be collected
- Data provided by the users
- Amazon Mechanical Turk Worker ID
- Date of birth, sex, ethnicity, ocular alignment, refractive error, visual pathologies, use of glasses and observations
- Agreement on the informed consent
- Face images/videos
- Data collected while the users use Sevices
- Operation system and hardware specifications
- Log data, user interactions and use time
3. Responsible for data processing
Name: DIVE Medical, S.L. (hereinafter, “DIVE”)
Address: BIC Guipúzcoa
Paseo Miramón 170
20014 San Sebastián
Contact email: firstname.lastname@example.org
Your personal data will be processed exclusively for the research work referred to in this document. In the application you will be asked for express permission to give your images, date of birth, sex, ethnicity and information about visual pathologies to this research work. When conducting the experiment, a numerical identifier will be associated with your data so that it cannot be linked to your name. As images of your face will be collected, it is considered that a complete anonymization or pseudonymization is not possible. However, these images will always be analyzed by automated computer methods, without requiring viewing by the researchers. In addition, to ensure data protection, the data will always be password-encrypted, and the device on which the data will be collected and stored will also be password-protected.
The processing of the data in this study is legitimized by your consent to participate.
No data will be transferred to third parties unless legally obliged to do so. The only persons who will have access to the data of the present experiment are the Principal Investigator, Marta Ortín Obón, and the collaborating researchers participating in the study.
It is expected that the data collected can be used for future research and to continue to evaluate improvements in the models created, so a backup copy of the data collected will be stored for approximately 10 years. The data will be destroyed on December 1, 2033. Any additional studies or projects conducted during the data retention period and making use of the data will go through the appropriate controls and authorizations. In addition, you may request the removal of your data at any time during the retention period by sending an e-mail to email@example.com. The exploited results, fully anonymized and without personal data, will be retained beyond this time.
You may exercise your rights of access, rectification, deletion and portability of your data, limitation and opposition to its processing, in accordance with the provisions of the LO 3/2018 on the Protection of Personal Data and guarantee of digital rights and the General Data Protection Regulation (GDPR 2016/679) to the Principal Investigator of the project, whose contact details are given in the heading of this document.
If your request is not met, you may contact the Spanish Data Protection Agency (https://www.aepd.es) to file a complaint when you consider that your rights have not been properly addressed.
Based on the results of the research work, scientific communications may be prepared to be presented at congresses or scientific journals, but they will always be done with grouped data and nothing that could identify you will ever be disclosed.
Date of publication: December 4th, 2023
Date of last update: December 4th, 2023