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...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/8/4138 |
| _version_ | 1797603532744949760 |
|---|---|
| author | Mohd Faizan Ansari Pawel Kasprowski Peter Peer |
| author_facet | Mohd Faizan Ansari Pawel Kasprowski Peter Peer |
| author_sort | Mohd Faizan Ansari |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-03-11T04:33:28Z |
| format | Article |
| id | doaj.art-dc3b103b7f664e0d89cbf064384e7b09 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T04:33:28Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-dc3b103b7f664e0d89cbf064384e7b092023-11-17T21:19:37ZengMDPI AGSensors1424-82202023-04-01238413810.3390/s23084138Person-Specific Gaze Estimation from Low-Quality Webcam ImagesMohd Faizan Ansari0Pawel Kasprowski1Peter Peer2Department of Applied Informatics, Silesian University of Technology, 44-100 Gliwice, PolandDepartment of Applied Informatics, Silesian University of Technology, 44-100 Gliwice, PolandFaculty of Computer and Information Science, University of Ljubljana, Večna Pot 113, SI-1000 Ljubljana, SloveniaGaze 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.https://www.mdpi.com/1424-8220/23/8/4138gaze estimationconvolution neural networkcomputer visiondeep learning |
| spellingShingle | Mohd Faizan Ansari Pawel Kasprowski Peter Peer Person-Specific Gaze Estimation from Low-Quality Webcam Images Sensors gaze estimation convolution neural network computer vision deep learning |
| 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 | gaze estimation convolution neural network computer vision deep learning |
| url | https://www.mdpi.com/1424-8220/23/8/4138 |
| work_keys_str_mv | AT mohdfaizanansari personspecificgazeestimationfromlowqualitywebcamimages AT pawelkasprowski personspecificgazeestimationfromlowqualitywebcamimages AT peterpeer personspecificgazeestimationfromlowqualitywebcamimages |