Contactless Real-Time Eye Gaze-Mapping System Based on Simple Siamese Networks
Human–computer interaction (HCI) is a multidisciplinary field that investigates the interactions between humans and computer systems. HCI has facilitated the development of various digital technologies that aim to deliver optimal user experiences. Gaze recognition is a critical aspect of HCI, as it...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/9/5374 |
| _version_ | 1827743261569056768 |
|---|---|
| author | Hoyeon Ahn Jiwon Jeon Donghwuy Ko Jeonghwan Gwak Moongu Jeon |
| author_facet | Hoyeon Ahn Jiwon Jeon Donghwuy Ko Jeonghwan Gwak Moongu Jeon |
| author_sort | Hoyeon Ahn |
| collection | DOAJ |
| description | Human–computer interaction (HCI) is a multidisciplinary field that investigates the interactions between humans and computer systems. HCI has facilitated the development of various digital technologies that aim to deliver optimal user experiences. Gaze recognition is a critical aspect of HCI, as it can provide valuable insights into basic human behavior. The gaze-matching method is a reliable approach that can identify the area at which a user is looking. Early methods of gaze tracking required users to wear glasses with a tracking function and limited tracking to a small monitoring area. Additionally, gaze estimation was restricted to a fixed posture within a narrow range. In this study, we proposed a novel non-contact gaze-mapping system that could overcome the physical limitations of previous methods and be applied in real-world environments. Our experimental results demonstrated an average gaze-mapping accuracy of 92.9% across 9 different test environments. Moreover, we introduced the GIST gaze-mapping (GGM) dataset, which served as a valuable resource for learning and evaluating gaze-mapping techniques. |
| first_indexed | 2024-03-11T04:24:03Z |
| format | Article |
| id | doaj.art-3b3d7fe79ec44c5499abb0a20ea3acde |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T04:24:03Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-3b3d7fe79ec44c5499abb0a20ea3acde2023-11-17T22:33:11ZengMDPI AGApplied Sciences2076-34172023-04-01139537410.3390/app13095374Contactless Real-Time Eye Gaze-Mapping System Based on Simple Siamese NetworksHoyeon Ahn0Jiwon Jeon1Donghwuy Ko2Jeonghwan Gwak3Moongu Jeon4School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of KoreaTmaxTibero, 258, Hwangsaeul-ro, Bundang-gu, Seongnam 13595, Republic of KoreaAhnLab, Inc., 220, Pangyoyeok-ro, Bundang-gu, Seongnam 13493, Republic of KoreaDepartment of Software, Korea National University of Transportation, Chungju 27469, Republic of KoreaSchool of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of KoreaHuman–computer interaction (HCI) is a multidisciplinary field that investigates the interactions between humans and computer systems. HCI has facilitated the development of various digital technologies that aim to deliver optimal user experiences. Gaze recognition is a critical aspect of HCI, as it can provide valuable insights into basic human behavior. The gaze-matching method is a reliable approach that can identify the area at which a user is looking. Early methods of gaze tracking required users to wear glasses with a tracking function and limited tracking to a small monitoring area. Additionally, gaze estimation was restricted to a fixed posture within a narrow range. In this study, we proposed a novel non-contact gaze-mapping system that could overcome the physical limitations of previous methods and be applied in real-world environments. Our experimental results demonstrated an average gaze-mapping accuracy of 92.9% across 9 different test environments. Moreover, we introduced the GIST gaze-mapping (GGM) dataset, which served as a valuable resource for learning and evaluating gaze-mapping techniques.https://www.mdpi.com/2076-3417/13/9/5374human–computer interactiongaze mappingfacial detectionfacial recognition |
| spellingShingle | Hoyeon Ahn Jiwon Jeon Donghwuy Ko Jeonghwan Gwak Moongu Jeon Contactless Real-Time Eye Gaze-Mapping System Based on Simple Siamese Networks Applied Sciences human–computer interaction gaze mapping facial detection facial recognition |
| title | Contactless Real-Time Eye Gaze-Mapping System Based on Simple Siamese Networks |
| title_full | Contactless Real-Time Eye Gaze-Mapping System Based on Simple Siamese Networks |
| title_fullStr | Contactless Real-Time Eye Gaze-Mapping System Based on Simple Siamese Networks |
| title_full_unstemmed | Contactless Real-Time Eye Gaze-Mapping System Based on Simple Siamese Networks |
| title_short | Contactless Real-Time Eye Gaze-Mapping System Based on Simple Siamese Networks |
| title_sort | contactless real time eye gaze mapping system based on simple siamese networks |
| topic | human–computer interaction gaze mapping facial detection facial recognition |
| url | https://www.mdpi.com/2076-3417/13/9/5374 |
| work_keys_str_mv | AT hoyeonahn contactlessrealtimeeyegazemappingsystembasedonsimplesiamesenetworks AT jiwonjeon contactlessrealtimeeyegazemappingsystembasedonsimplesiamesenetworks AT donghwuyko contactlessrealtimeeyegazemappingsystembasedonsimplesiamesenetworks AT jeonghwangwak contactlessrealtimeeyegazemappingsystembasedonsimplesiamesenetworks AT moongujeon contactlessrealtimeeyegazemappingsystembasedonsimplesiamesenetworks |