Cargando…
Person-Specific Gaze Estimation from Low-Quality Webcam Images
Gaze estimation is an established research problem in computer vision. It has various applications in real life, from human–computer interactions to health care and virtual reality, making it more viable for the research community. Due to the significant success of deep learning techniques in other...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10147084/ https://www.ncbi.nlm.nih.gov/pubmed/37112478 http://dx.doi.org/10.3390/s23084138 |
_version_ | 1785034731534942208 |
---|---|
author | Ansari, Mohd Faizan Kasprowski, Pawel Peer, Peter |
author_facet | Ansari, Mohd Faizan Kasprowski, Pawel Peer, Peter |
author_sort | Ansari, Mohd Faizan |
collection | PubMed |
description | Gaze estimation is an established research problem in computer vision. It has various applications in real life, from human–computer interactions to health care and virtual reality, making it more viable for the research community. Due to the significant success of deep learning techniques in other computer vision tasks—for example, image classification, object detection, object segmentation, and object tracking—deep learning-based gaze estimation has also received more attention in recent years. This paper uses a convolutional neural network (CNN) for person-specific gaze estimation. The person-specific gaze estimation utilizes a single model trained for one individual user, contrary to the commonly-used generalized models trained on multiple people’s data. We utilized only low-quality images directly collected from a standard desktop webcam, so our method can be applied to any computer system equipped with such a camera without additional hardware requirements. First, we used the web camera to collect a dataset of face and eye images. Then, we tested different combinations of CNN parameters, including the learning and dropout rates. Our findings show that building a person-specific eye-tracking model produces better results with a selection of good hyperparameters when compared to universal models that are trained on multiple users’ data. In particular, we achieved the best results for the left eye with 38.20 MAE (Mean Absolute Error) in pixels, the right eye with 36.01 MAE, both eyes combined with 51.18 MAE, and the whole face with 30.09 MAE, which is equivalent to approximately 1.45 degrees for the left eye, 1.37 degrees for the right eye, 1.98 degrees for both eyes combined, and 1.14 degrees for full-face images. |
format | Online Article Text |
id | pubmed-10147084 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-101470842023-04-29 Person-Specific Gaze Estimation from Low-Quality Webcam Images Ansari, Mohd Faizan Kasprowski, Pawel Peer, Peter Sensors (Basel) Article Gaze estimation is an established research problem in computer vision. It has various applications in real life, from human–computer interactions to health care and virtual reality, making it more viable for the research community. Due to the significant success of deep learning techniques in other computer vision tasks—for example, image classification, object detection, object segmentation, and object tracking—deep learning-based gaze estimation has also received more attention in recent years. This paper uses a convolutional neural network (CNN) for person-specific gaze estimation. The person-specific gaze estimation utilizes a single model trained for one individual user, contrary to the commonly-used generalized models trained on multiple people’s data. We utilized only low-quality images directly collected from a standard desktop webcam, so our method can be applied to any computer system equipped with such a camera without additional hardware requirements. First, we used the web camera to collect a dataset of face and eye images. Then, we tested different combinations of CNN parameters, including the learning and dropout rates. Our findings show that building a person-specific eye-tracking model produces better results with a selection of good hyperparameters when compared to universal models that are trained on multiple users’ data. In particular, we achieved the best results for the left eye with 38.20 MAE (Mean Absolute Error) in pixels, the right eye with 36.01 MAE, both eyes combined with 51.18 MAE, and the whole face with 30.09 MAE, which is equivalent to approximately 1.45 degrees for the left eye, 1.37 degrees for the right eye, 1.98 degrees for both eyes combined, and 1.14 degrees for full-face images. MDPI 2023-04-20 /pmc/articles/PMC10147084/ /pubmed/37112478 http://dx.doi.org/10.3390/s23084138 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Ansari, Mohd Faizan Kasprowski, Pawel Peer, Peter Person-Specific Gaze Estimation from Low-Quality Webcam Images |
title | Person-Specific Gaze Estimation from Low-Quality Webcam Images |
title_full | Person-Specific Gaze Estimation from Low-Quality Webcam Images |
title_fullStr | Person-Specific Gaze Estimation from Low-Quality Webcam Images |
title_full_unstemmed | Person-Specific Gaze Estimation from Low-Quality Webcam Images |
title_short | Person-Specific Gaze Estimation from Low-Quality Webcam Images |
title_sort | person-specific gaze estimation from low-quality webcam images |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10147084/ https://www.ncbi.nlm.nih.gov/pubmed/37112478 http://dx.doi.org/10.3390/s23084138 |
work_keys_str_mv | AT ansarimohdfaizan personspecificgazeestimationfromlowqualitywebcamimages AT kasprowskipawel personspecificgazeestimationfromlowqualitywebcamimages AT peerpeter personspecificgazeestimationfromlowqualitywebcamimages |