Görünüm ve Özellik Tabanlı Bir Bakış İzleme Modelinin Geliştirilmesi: TrGaze24

Year 2026, Volume: 9 Issue: 1 , 29 - 54 , 14.01.2026

Adem Mehmet Yıldız , Ömer Kırmacı , Adem Uzun , Mehmet Demirbağ

https://doi.org/10.47495/okufbed.1657375

https://izlik.org/JA73XS55ST

Abstract

Bu çalışmada, çok modlu analitikler için bakış noktaları ile açılarını tahmin etmek amacıyla görünüm ve özellik tabanlı yöntemlere dayalı bir bakış izleme modeli geliştirilmiştir. İlk olarak bir göz veri seti oluşturulmuştur. Veri toplama sürecinde, 25 noktalı bir kalibrasyon tasarımı kullanılarak laboratuvar ortamında 128 katılımcıdan veri elde edilmiştir. TrGaze24 adını verdiğimiz veri setinden tahmin modeli oluşturmak için bir evrişimli sinir ağı (CNN) tasarlanmış ve yüz görüntülerinden çıkarılan sağ ve sol gözlere ait 18.410 göz görüntüsü, göz açıları ve yüz özellikleri modele girdi olarak sunulmuştur. Çıktılar, ekran üzerindeki hedef noktaların x ve y koordinatları ile bakış açısı vektörleri şeklinde belirlenmiştir. Modelin performansı için ortalama mutlak hatalar hesaplanmıştır, bakışa ait noktasal uzaklıkların tahminlerinde 3,74 cm ve açısal vektörlerin tahminlerinde 3,32 derece hata oranıyla literatürdeki benzer çalışmalara kıyasla oldukça başarılı bulunmuştur. Özellikle eğitim teknolojileri açısından, bilgisayar destekli eğitim ortamlarında web kamerası tabanlı bakış izleme sistemlerin temelini oluşturma potansiyeli taşımaktadır. Bu model, öğrenme analitiklerinde bilişsel süreçlerin incelenmesine olanak tanırken, aynı zamanda psikoloji, reklamcılık ve sosyal bilimler gibi alanlarda da kullanılabilirliğiyle dikkat çekmektedir.

Keywords

Bakış izleme modeli , Göz veri seti , Göz izleme , Evrişimli sinir ağı mimarisi

Development of an Appearance- and Feature-Based Gaze Tracking Model: TrGaze24

https://izlik.org/JA73XS55ST

Abstract

This study developed a gaze tracking model based on appearance- and feature-based methods to predict gaze points and angles within the scope of multimodal analytics. First, an eye dataset was created. During the data collection process, data were obtained from 128 participants in a laboratory setting using a 25-point calibration design. To create a prediction model from the dataset, which we named TrGaze24, a convolutional neural network (CNN) was designed. The model utilized 18,410 eye images (right and left eyes) extracted from facial data, along with gaze angles and facial features, as inputs. The outputs were defined as the x and y coordinates of target points on the screen and gaze direction vectors. The model's performance was evaluated by calculating mean absolute errors, with point-based gaze predictions showing an error of 3,74 cm and angular vector predictions an error of 3.32 degrees. These results demonstrated significant success compared to similar studies in the literature. Particularly in educational technologies, the model holds potential to form the foundation of webcam-based gaze tracking systems in computer-assisted learning environments. In addition to enabling the analysis of cognitive processes in learning analytics, the model also stands out for its applicability in fields such as psychology, advertising, and social sciences.

Keywords

Gaze tracking model , Eye dataset , Eye tracking , Convolutional neural network architecture

References

• Akinyelu AA., Blignaut P. Convolutional neural network-based methods for eye gaze estimation: a survey. IEEE Access 2020; 8: 581-605. https://doi.org/10.1109/ACCESS.2020.3013540
• Altan T., Çağiltay K. An eye-tracking analysis of spatial contiguity effect in educational animations. Learning and Collaboration Technologies: Second International Conference 2023; 3-13, Los Angeles, CA, USA. https://doi.org/10.1007/978-3-319-20609-7_1
• Baluja S., Pomerleau D. Non-intrusive gaze tracking using artificial neural networks. Advances in Neural Information Processing Systems 1993; 753-760.
• Bondareva D., Conati C., Feyzi-Behnagh R., Harley JM., Azevedo R., Bouchet F. Inferring learning from gaze data during interaction with an environment to support self-regulated learning. In: H. C. Lane, K. Yacef, J. Mostow, P. Pavlik (Ed.), Artificial intelligence in education. Springer 2013; 229-238. https://doi.org/10.1007/978-3-642-39112-5_24
• Buswell GT. How people look at pictures: a study of the psychology and perception in art. Univ Chicago Press 1935.
• Chennamma HR., Yuan X. A survey on eye-gaze tracking techniques. arXiv preprint arXiv:1312.6410, 2013; https://doi.org/10.48550/arXiv.1312.6410
• Chong E., Ruiz N., Wang Y., Zhang Y., Rozga A., Rehg JM. Connecting gaze, scene, and attention: generalized attention estimation via joint modelling of gaze and scene saliency. In Proceedings of the European conference on Computer Vision 2018; 383-398. https://doi.org/10.1007/978-3-030-01228-1_24/FIGURES/7
• Crescenzi-Lanna L. Multimodal learning analytics research with young children: a systematic review. British Journal of Educational Technology 2020; 51(5): 1485-1504. https://doi.org/10.1111/BJET.12959
• Davis EK. dlib Library 2015; https://github.com/davisking/dlib. (Erişim tarihi: 11 Ekim 2024).
• Delabarre EB. A method of recording eye-movements. The American Journal of Psychology 1898; 9(4): 572-574. https://doi.org/10.2307/1412191
• Demjén E., Aboši V., Tomori Z. Eye tracking using artificial neural networks for human computer interaction. Physiological Research 2011; 60(5): 841-844. https://doi.org/10.33549/physiolres.932117
• Duchowski AT. Eye tracking methodology: Theory and practice. Springer International Publishing 2017. Falch L., Lohan KS. Webcam-based gaze estimation for computer screen interaction. Frontiers in Robotics and AI 2024; 11. https://doi.org/10.3389/FROBT.2024.1369566/BIBTEX
• Fischer T., Chang HJ., Demiris Y. RT-GENE: Real-time eye gaze estimation in natural environments. In: Proceedings of the European Conference on Computer Vision 2018; 334-352. https://openaccess.thecvf.com/content_ECCV_2018/html/Tobias_Fischer_RT-GENE_Real-Time_Eye_ECCV_2018_paper.html
• Frischen A., Bayliss AP., Tipper SP. Gaze cueing of attention: visual attention, social cognition, and individual differences. Psychological Bulletin 2007; 133(4): 694-724. https://doi.org/10.1037/0033-2909.133.4.694
• Ghosh S., Dhall A., Hayat M., Knibbe J., Ji Q. automatic gaze analysis: a survey of deep learning-based approaches. IEEE Transactions on Pattern Analysis and Machine Intelligence 2024; 46(1): 61-84. https://doi.org/10.1109/TPAMI.2023.3321337
• Goldberg JH., Stimson MJ., Lewenstein M., Scott N., Wichansky AM. Eye tracking in web search tasks: design implications. Proceedings of the 2002 Symposium on Eye Tracking Research & Applications 2002; 51-58. https://doi.org/10.1145/507072.507082
• google-ai-edge/mediapipe. GitHub- google-ai-edge/mediapipe: Cross-platform, customizable ml solutions for live and streaming media 2020; https://github.com/google-ai-edge/mediapipe. (Erişim tarihi: 11 Ekim 2024)
• Greene HH., Rayner K. Eye movements and familiarity effects in visual search. Vision Research 2001; 41(27): 3763-3773. https://doi.org/10.1016/S0042-6989(01)00154-7
• Grillon H., Françoise R., Bruno H., Daniel T. Use of virtual reality as therapeutic tool for behavioural exposure in the ambit of social. In International Conference Series on Disability, Virtual Reality and Associated Technologies 2006.
• Hansen DW., Ji Q. In the eye of the beholder: a survey of models for eyes and gaze. IEEE Transactions on Pattern Analysis and Machine Intelligence 2010; 32(3): 478-500. https://doi.org/10.1109/TPAMI.2009.30
• Huang Q., Veeraraghavan A., Sabharwal A. TabletGaze: unconstrained appearance-based gaze estimation in mobile tablets. arXiv 2016; https://doi.org/10.48550/arXiv.1508.01244
• Huey EB. Preliminary experiments in the physiology and psychology of reading. The American Journal of Psychology 1898; 9(4): 575-586. https://doi.org/10.2307/1412192
• Iannizzotto G., La Rosa F. Competitive combination of multiple eye detection and tracking techniques. IEEE Transactions on Industrial Electronics 2011; 58(8): 3151-3159. https://doi.org/10.1109/TIE.2010.2102314
• Jacob RJK. What you look at is what you get: eye movement-based interaction techniques. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems 1990; 11-18. https://doi.org/10.1145/97243.97246
• Jongerius C., Callemein T., Goedemé T., Van Beeck K., Romijn JA., Smets EMA., Hillen MA. Eye-tracking glasses in face-to-face interactions: manual versus automated assessment of areas-of-interest. Behavior Research Methods 2021; 53(5): 2037-2048. https://doi.org/10.3758/s13428-021-01544-2
• Jabbarlı G., Kurt M. LightFFDNets: Lightweight convolutional neural networks for rapid facial forgery detection. arXiv 2024. https://doi.org/10.48550/arXiv.2411.11826
• Just MA., Carpenter PA. Eye fixations and cognitive processes. Cognitive Psychology 1976; 8(4): 441-480. https://doi.org/10.1016/0010-0285(76)90015-3
• Kazemi V., Sullivan J. One millisecond face alignment with an ensemble of regression trees. 2014 IEEE Conference on Computer Vision and Pattern Recognition 2014; 1867-1874. https://doi.org/10.1109/CVPR.2014.241
• Kellnhofer P., Recasens A., Stent S., Matusik W., Torralba A. Gaze360: Physically unconstrained gaze estimation in the wild. arXiv 2019; https://doi.org/10.48550/arXiv.1910.10088
• Krafka K., Khosla A., Kellnhofer P., Kannan H., Bhandarkar S., Matusik W., Torralba A. Eye tracking for everyone. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016; 2176-2184. https://doi.org/10.1109/CVPR.2016.239
• Lian D., Zhang Z., Luo W., Hu L., Wu M., Li Z., Yu J., Gao S. RGBD based gaze estimation via multi-task cnn. Proceedings of the AAAI Conference on Artificial Intelligence 2019; 33(01): 2488-2495. https://doi.org/10.1609/AAAI.V33I01.33012488
• Liu J., Chi J., Yang H., Yin X. In the eye of the beholder: a survey of gaze tracking techniques. Pattern Recognition 2022; 132: 108944. https://doi.org/10.1016/j.patcog.2022.108944
• Lopes A., Ward AD., Cecchini M. Eye tracking in digital pathology: a comprehensive literature review. Journal of Pathology Informatics 2024; 15: 100383. https://doi.org/10.1016/J.JPI.2024.100383
• Lu F., Chen X., Sato Y. Appearance-based gaze estimation via uncalibrated gaze pattern recovery. IEEE Transactions on Image Processing 2017; 26(4): 1543-1553. https://doi.org/10.1109/TIP.2017.2657880
• Lu F., Okabe T., Sugano Y., Sato Y. A head pose-free approach for appearance-based gaze estimation. Procedings of the British Machine Vision Conference 2011; 126: 1-11. https://doi.org/10.5244/C.25.126
• Lu F., Okabe T., Sugano Y., Sato Y. Learning gaze biases with head motion for head pose-free gaze estimation. Image and Vision Computing 2014; 32(3): 169-179. https://doi.org/10.1016/j.imavis.2014.01.005
• Lu F., Sugano Y., Okabe T., Sato Y. Head pose-free appearance-based gaze sensing via eye image synthesis. Proceedings of the 21st International Conference on Pattern Recognition 2012; 1008-1011. https://ieeexplore.ieee.org/abstract/document/6460306
• Mahanama B., Jayawardana Y., Jayarathna S. Gaze-Net: Appearance-based gaze estimation using capsule networks. In Proceedings of the 11th Augmented Human International Conference 2020; 1-14. https://doi.org/10.1145/3396339.3396393
• Majaranta P., Räihä KJ. Twenty years of eye typing: systems and design issues. In Proceedings of the 2002 Symposium on Eye Tracking Research & Applications 2002; 15-22. https://doi.org/10.1145/507072.507076
• Mora KAF., Odobez JM. Gaze estimation from multimodal kinect data. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops 2012; 25-30. https://doi.org/10.1109/CVPRW.2012.6239182 Orozco J., Roca FX., Gonzàlez J. Real-time gaze tracking with appearance-based models. Machine Vision and Applications 2009; 20(6): 353-364. https://doi.org/10.1007/s00138-008-0130-6
• Palmero C., Selva J., Bagheri MA., Escalera S. Recurrent CNN for 3D Gaze estimation using appearance and shape cues. British Machine Vision Conference 2018; https://arxiv.org/abs/1805.03064v3
• Park S., Aksan E., Zhang X., Hilliges O. Towards end-to-end video-based eye-tracking. In: Computer Vision–ECCV 2020: 16th European Conference 2020; 747-763. Glasgow, UK. https://doi.org/10.48550/arXiv.2007.13120
• Pathirana P., Senarath S., Meedeniya D., Jayarathna S. Eye gaze estimation: a survey on deep learning-based approaches. Expert Systems with Applications 2022; 199: 116894. https://doi.org/10.1016/J.ESWA.2022.116894
• Porta M., Ricotti S., Perez CJ. Emotional e-learning through eye tracking. Proceedings of the 2012 IEEE Global Engineering Education Conference (EDUCON) 2012; 1-6. https://doi.org/10.1109/EDUCON.2012.6201145
• Radach R., Hyona J., Deubel H. The mind’s eye: cognitive and applied aspects of eye movement research. Elsevier 2003.
• Rayner K. Eye movements in reading and information processing: 20 years of research. Psychological Bulletin 1998; 124(3): 372-422. https://doi.org/10.1037/0033-2909.124.3.372
• Rayner K., Rotello CM., Stewart AJ., Keir J., Duffy SA. Integrating text and pictorial information: eye movements when looking at print advertisements. Journal of Experimental Psychology: Applied 2001; 7(3):219-226. https://doi.org/10.1037/1076-898X.7.3.219
• Reale M., Hung T., Yin L. Pointing with the eyes: gaze estimation using a static/active camera system and 3d iris disk model. 2010 IEEE International Conference on Multimedia and Expo 2010; 280-285. https://doi.org/10.1109/ICME.2010.5583014
• Rikert TD., Jones J. Gaze estimation using morphable models. Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition 1998; 436-441. https://doi.org/10.1109/AFGR.1998.670987
• Sağlam Z., Yilmaz FGK. Eğitim araştırmalarında göz izleme: araştırmalardaki eğilimlerin belirlenmesi. Gazi Üniversitesi Gazi Eğitim Fakültesi Dergisi 2021; 41(3): 1621-1649. https://dergipark.org.tr/en/pub/gefad/issue/67470/892733
• Saxena S., Fink LK., Lange EB. Deep learning models for webcam eye tracking in online experiments. Behavior Research Methods 2023; 56: 3487–3503. https://doi.org/10.3758/s13428-023-02190-6
• Sewell W., Komogortsev O. Real-time eye gaze tracking with an unmodified commodity webcam employing a neural network. CHI ’10 Extended Abstracts on Human Factors in Computing Systems 2010; 3739-3744. https://doi.org/10.1145/1753846.1754048
• Sharma K., Giannakos M., Dillenbourg P. Eye-tracking and artificial intelligence to enhance motivation and learning. Smart Learning Environments 2020; 7(1): 13. https://doi.org/10.1186/s40561-020-00122-x
• Sigut J., Sidha SA. Iris center corneal reflection method for gaze tracking using visible light. IEEE Transactions on Biomedical Engineering 2011; 58(2): 411-419. https://doi.org/10.1109/TBME.2010.2087330
• Smith BA., Yin Q., Feiner SK., Nayar SK. Gaze locking: passive eye contact detection for human-object interaction. Proceedings of the 26th Annual ACM Symposium on User Interface Software and Technology 2013; 271-280. https://doi.org/10.1145/2501988.2501994
• Snodderly DM., Kagan I., Gur M. Selective activation of visual cortex neurons by fixational eye movements: implications for neural coding. Visual Neuroscience 2001; 18(2): 259-277. https://doi.org/10.1017/S0952523801182118
• Sugano Y., Matsushita Y., Sato Y. Appearance-based gaze estimation using visual saliency. IEEE Transactions on Pattern Analysis and Machine Intelligence 2013; 35(2): 329-341. https://doi.org/10.1109/TPAMI.2012.101
• Sugano Y., Matsushita Y., Sato Y. Learning-by-synthesis for appearance-based 3d gaze estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2014; 1821-1828.
• Taba IB. Improving eye-gaze tracking accuracy through personalized calibration of a user’s aspherical corneal model. University of British Columbia. PhD Thesis. 2012; 122. https://doi.org/10.14288/1.0072558
• Tan KH., Kriegman DJ., Ahuja N. Appearance-based eye gaze estimation. Sixth IEEE Workshop on Applications of Computer Vision 2002; 191-195. https://doi.org/10.1109/ACV.2002.1182180
• Tinker MA. Eye movements in reading. The Journal of Educational Research 1936; 30(4): 241-277. https://www.jstor.org/stable/27526226
• Torricelli D., Conforto S., Schmid M., D’Alessio T. A neural-based remote eye gaze tracker under natural head motion. Computer Methods and Programs in Biomedicine 2008; 92(1): 66-78. https://doi.org/10.1016/j.cmpb.2008.06.008
• Viola P., Jones MJ. Robust real-time face detection. International Journal of Computer Vision 2004; 57(2): 137-154. https://doi.org/10.1023/B:VISI.0000013087.49260.fb
• Xu H., Zhang J., Sun H., Qi M., Kong J. Analyzing students’ attention by gaze tracking and object detection in classroom teaching. Data Technologies and Applications 2023; 57(5): 643-667. https://doi.org/10.1108/DTA-09-2021-0236/FULL/PDF
• Xu X., Chen J., Li C., Fu C., Yang L., Yan Y., Lyu Z. Robust gaze point estimation for metaverse with common mode features suppression network. IEEE Transactions on Consumer Electronics 2024; 70(1): 2090-2098. https://doi.org/10.1109/TCE.2024.3351190
• Yang XH., Sun JD., Liu J., Li XC., Yang CX., Liu W. A remote gaze tracking system using gray-distribution-based video processing. Biomedical Engineering: Applications, Basis and Communications 2012; 24(03): 217-227. https://doi.org/10.4015/S1016237212500044
• Yecan E., Çaǧiltay K. Cognitive styles and students’ interaction with an instructional website: tracing users through eye-gaze. In Sixth IEEE International Conference on Advanced Learning Technologies 2006; 340-342. https://doi.org/10.1109/ICALT.2006.1652438
• Zhang X., Park S., Beeler T., Bradley D., Tang S., Hilliges O. ETH-XGaze: A large-scale dataset for gaze estimation under extreme head pose and gaze variation. arXiv 2020; 365-381. https://doi.org/10.48550/arXiv.2007.15837
• Zhang X., Sugano Y., Fritz M., Bulling A. Appearance-based gaze estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015; 4511-4520.
• Zhang X., Sugano Y., Fritz M., Bulling A. It’s written all over your face: full-face appearance-based gaze estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops 2017; 51-60.
• Zhang X., Sugano Y., Fritz M., Bulling A. MPIIGaze: real-world dataset and deep appearance-based gaze estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence 2019; 41(1): 162-175. https://doi.org/10.1109/TPAMI.2017.2778103.