{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:44:12Z","timestamp":1776887052047,"version":"3.51.2"},"reference-count":32,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2020,9,9]],"date-time":"2020-09-09T00:00:00Z","timestamp":1599609600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2019R1I1A3A01042506"],"award-info":[{"award-number":["2019R1I1A3A01042506"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>As the demand for human-friendly computing increases, research on pupil tracking to facilitate human\u2013machine interactions (HCIs) is being actively conducted. Several successful pupil tracking approaches have been developed using images and a deep neural network (DNN). However, common DNN-based methods not only require tremendous computing power and energy consumption for learning and prediction; they also have a demerit in that an interpretation is impossible because a black-box model with an unknown prediction process is applied. In this study, we propose a lightweight pupil tracking algorithm for on-device machine learning (ML) using a fast and accurate cascade deep regression forest (RF) instead of a DNN. Pupil estimation is applied in a coarse-to-fine manner in a layer-by-layer RF structure, and each RF is simplified using the proposed rule distillation algorithm for removing unimportant rules constituting the RF. The goal of the proposed algorithm is to produce a more transparent and adoptable model for application to on-device ML systems, while maintaining a precise pupil tracking performance. Our proposed method experimentally achieves an outstanding speed, a reduction in the number of parameters, and a better pupil tracking performance compared to several other state-of-the-art methods using only a CPU.<\/jats:p>","DOI":"10.3390\/s20185141","type":"journal-article","created":{"date-parts":[[2020,9,9]],"date-time":"2020-09-09T09:01:09Z","timestamp":1599642069000},"page":"5141","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Energy Efficient Pupil Tracking Based on Rule Distillation of Cascade Regression Forest"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7452-3897","authenticated-orcid":false,"given":"Sangwon","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Keimyung University, Daegu 42601, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mira","family":"Jeong","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Keimyung University, Daegu 42601, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7284-0768","authenticated-orcid":false,"given":"Byoung Chul","family":"Ko","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Keimyung University, Daegu 42601, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,9,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"He, J., Pham, K., Valliappan, N., Xu, P., Roberts, C., Lagun, D., and Navalpakkam, V. (2019, January 27\u201328). On-Device Few-Shot Personalization for Real-Time Gaze Estimation. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW 2019), Seoul, Korea.","DOI":"10.1109\/ICCVW.2019.00146"},{"key":"ref_2","first-page":"44","article-title":"Explainable Artificial Intelligence (XAI) Program","volume":"40","author":"Gunning","year":"2018","journal-title":"AI Mag."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Gilpin, L.H., Bau, D., Yuan, B.Z., Bajwa, A., Specter, M., and Kagal, L. (2018, January 1\u20133). Explaining Explanations: An Overview of Interpretability of Machine Learning. Proceedings of the 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA), Turin, Italy.","DOI":"10.1109\/DSAA.2018.00018"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Arrieta","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2177","DOI":"10.1007\/s00158-019-02467-5","article-title":"Predictive modelling to support sensitivity analysis for robust design in aerospace engineering","volume":"61","author":"Dasari","year":"2020","journal-title":"Struct. Multidiscip. Optim."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1214\/15-AOAS848","article-title":"Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model","volume":"9","author":"Letham","year":"2015","journal-title":"Ann. Appl. Stat."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Yang, H., Rudin, C., and Seltzer, M. (2017, January 7\u20139). Scalable Bayesian Rule Lists. Proceedings of the 34th International Conference on Machine Learning (ICML), Sydney, Australia.","DOI":"10.32614\/CRAN.package.sbrl"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data mining (KDD), San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Kim, S., Jeong, M., and Ko, B.C. (2020, September 08). Interpretation and Simplification of Deep Forest. Available online: https:\/\/www.techrxiv.org\/articles\/Interpretation_and_Simplification_of_Deep_Forest\/11661246\/1.","DOI":"10.36227\/techrxiv.11661246.v1"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.imavis.2018.01.003","article-title":"Hybrid eye center localization using cascaded regression and hand-crafted model fitting","volume":"71","author":"Levinshtein","year":"2018","journal-title":"Image Vis. Comput."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.cviu.2018.02.002","article-title":"PuRe: Robust pupil detection for real-time pervasive eye tracking","volume":"170","author":"Santini","year":"2018","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1364\/JOSAA.33.000314","article-title":"Eye center localization and gaze gesture recognition for human\u2013computer interaction","volume":"33","author":"Zhang","year":"2016","journal-title":"J. Opt. Soc. Am. A"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1007\/s11042-019-08160-5","article-title":"Hybrid regression and isophote curvature for accurate eye center localization","volume":"79","author":"Xia","year":"2019","journal-title":"Multimed. Tools Appl."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1093\/comjnl\/bxy102","article-title":"A Low-Cost Pupil Center Localization Algorithm Based on Maximized Integral Voting of Circular Hollow Kernels","volume":"62","author":"Ince","year":"2018","journal-title":"Comput. J."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1049\/iet-cvi.2015.0316","article-title":"Fast and accurate algorithm for eye localisation for gaze tracking in low-resolution images","volume":"10","author":"George","year":"2016","journal-title":"IET Comput. Vis."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1109\/JAS.2019.1911684","article-title":"Accurate and robust eye center localization via fully convolutional networks","volume":"6","author":"Xia","year":"2019","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1016\/j.patcog.2018.12.014","article-title":"Cascade learning from adversarial synthetic images for accurate pupil detection","volume":"88","author":"Gou","year":"2019","journal-title":"Pattern Recognit."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Choi, J.H., Lee, K.I., Kim, Y.C., and Song, B.C. (2019, January 22\u201325). Accurate Eye Pupil Localization Using Heterogeneous CNN Models. Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan.","DOI":"10.1109\/ICIP.2019.8803121"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Yu, Y., Liu, G., and Odobez, J.-M. (2019, January 16\u201320). Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01221"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Park, S., De Mello, S., Molchanov, P., Iqbal, U., Hilliges, O., and Kautz, J. (November, January 27). Few-Shot Adaptive Gaze Estimation. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.","DOI":"10.1109\/ICCV.2019.00946"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Krafka, K., Khosla, A., Kellnhofer, P., Kannan, H., Bhandarkar, S., Matusik, W., and Torralba, A. (July, January 26). Eye Tracking for Everyone. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.239"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lorenz, O., and Thomas, U. (2019, January 25\u201327). Real Time Eye Gaze Tracking System using CNN-based Facial Features for Human Attention Measurement. Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019), Prague, Czech Republic.","DOI":"10.5220\/0007565305980606"},{"key":"ref_23","unstructured":"Molnar, C. (2019). Interpretable Model. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable, Leanpub."},{"key":"ref_24","first-page":"1755","article-title":"Dlib-ml: A Machine Learning Toolkit","volume":"10","author":"King","year":"2009","journal-title":"J. Mach Learn Res."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Jesorsky, O., Kirchberg, K.J., and Frischholz, R.W. (2001, January 6\u20138). Robust Face Detection Using the Hausdorff Distance. Proceedings of the Audio- and Video-Based Biometric Person Authentication, Halmstad, Sweden.","DOI":"10.1007\/3-540-45344-X_14"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2501643.2501647","article-title":"Hybrid method based on topography for robust detection of iris center and eye corners","volume":"9","author":"Villanueva","year":"2013","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1049\/el.2018.0123","article-title":"Eye centre localisation with hybrid regression framework","volume":"54","author":"Li","year":"2018","journal-title":"Electron. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ahmed, N.Y. (2020). Real-time accurate eye center localization for low-resolution grayscale images. J. Real-Time Image Process., 1\u201328.","DOI":"10.1007\/s11554-020-00955-2"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_30","unstructured":"Simonyan, K., and Zisserman, A. (2020, September 08). Very deep convolutional networks for large-scale image recognition. Available online: https:\/\/arxiv.org\/abs\/1409.1556."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for MobileNetV3. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"123611","DOI":"10.1016\/j.jclepro.2020.123611","article-title":"Novel leakage detection and water loss management of urban water supply network using multiscale neural networks","volume":"278","author":"Hu","year":"2020","journal-title":"J. Clean. Prod."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/18\/5141\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:08:24Z","timestamp":1760177304000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/18\/5141"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,9]]},"references-count":32,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["s20185141"],"URL":"https:\/\/doi.org\/10.3390\/s20185141","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,9]]}}}