A Robust Framework for Real-Time Iris Landmarks Detection Using Deep Learning
Source abstract
Abstract
Iris detection and tracking plays a vital role in human–computer interaction and has become an emerging field for researchers in the last two decades. Typical applications such as virtual reality, augmented reality, gaze detection for customer behavior, controlling computers, and handheld embedded devices need accurate and precise detection of iris landmarks. A significant improvement has been made so far in iris detection and tracking. However, iris landmarks detection in real-time with high accuracy is still a challenge and a computationally expensive task. This is also accompanied with the lack of a publicly available dataset of annotated iris landmarks. This article presents a benchmark dataset and a robust framework for the localization of key landmark points to extract the iris with better accuracy. A number of training sessions have been conducted for MobileNetV2, ResNet50, VGG16, and VGG19 over an iris landmarks dataset, and ImageNet weights are used for model initialization. The Mean Absolute Error (MAE), model loss, and model size are measured to evaluate and validate the proposed model. Results analyses show that the proposed model outperforms other methods on selected parameters. The MAEs of MobileNetV2, ResNet50, VGG16, and VGG19 are 0.60, 0.33, 0.35, and 0.34; the average decrease in size is 60%, and the average reduction in response time is 75% compared to the other models. We collected the images of eyes and annotated them with the help of the proposed algorithm. The generated dataset has been made publicly available for research purposes. The contribution of this research is a model with a more diminutive size and the real-time and accurate prediction of iris landmarks, along with the provided dataset of iris landmark annotations.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Biometric Identification and Security · Genomic variations and chromosomal abnormalities · Face recognition and analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science, Attock Campus, COMSATS University Islamabad, Attock 43600, Pakistan
Department of Computer and Software Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology, Islamabad 46000, Pakistan
Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, Riyadh 11671, Saudi Arabia
References (36)
Show source-provided references
1. Use of iris pattern recognition to evaluate ocular torsional changes associated with head tilt
2. Lin, C., Li, X., Li, Z., and Hou, J. (2022). Finding Stars from Fireworks: Improving Non-Cooperative Iris Tracking. IEEE Trans. Circuits Syst. Video Technol.10.1109/TCSVT.2022.3158969 ↗
3. A robust perception based method for iris tracking10.1016/j.patrec.2014.09.001 ↗
4. Jose, F., Carvalho, S., Manuel, J., and Tavares, R. (2018). Two methodologies for iris detection and location in face images. Computational Modelling of Objects Represented in Images, CRC Press.
5. Liu, Y., Chen, C., Zhang, M., Li, J., and Xu, W. (2021, January 6–8). Joint Face Detection and Landmark Localization Based on an Extremely Lightweight Network. Proceedings of the International Conference on Image and Graphics, Haikou, China.10.1007/978-3-030-87358-5_28 ↗
6. Facial Landmark Based Region of Interest Localization for Deep Facial Expression Recognition
7. Li, J., Wang, Y., Wang, C., Tai, Y., Qian, J., Yang, J., Wang, C., Li, J., and Huang, F. (2019, January 15–20). DSFD: Dual shot face detector. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00520 ↗
8. Guo, X., Li, S., Yu, J., Zhang, J., Ma, J., Ma, L., Liu, W., and Ling, H. (1902). PFLD: A practical facial landmark detector. arXiv.
9. Ma, P., Martinez, B., Petridis, S., and Pantic, M. (2021, January 6–11). Towards practical lipreading with distilled and efficient models. Proceedings of the ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada.10.1109/ICASSP39728.2021.9415063 ↗
10. MTCD: Cataract detection via near infrared eye images10.1016/j.cviu.2021.103303 ↗
11. Eye tracking based control system for natural human-computer interaction10.1155/2017/5739301 ↗
12. Tonsen, M., Zhang, X., Sugano, Y., and Bulling, A. (2016, January 14–17). Labelled pupils in the wild: A dataset for studying pupil detection in unconstrained environments. Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications, Charleston, SC, USA.10.1145/2857491.2857520 ↗
13. Luo, B., Shen, J., Wang, Y., and Pantic, M. (2018, January 20–21). The iBUG eye segmentation dataset. Proceedings of the 2018 Imperial College Computing Student Workshop (ICCSW 2018), Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, London, UK.
14. A robust iris segmentation scheme based on improved U-net10.1109/ACCESS.2019.2924464 ↗
15. BIRD: Watershed based iris detection for mobile devices10.1016/j.patrec.2014.10.017 ↗
16. Sheela, S., and Abhinand, P. (2015, January 12–13). Iris detection for gaze tracking using video frames. Proceedings of the 2015 IEEE International Advance Computing Conference (IACC), Bangalore, India.10.1109/IADCC.2015.7154783 ↗
17. Khan, M.T., Arora, D., and Shukla, S. (2013, January 8–10). Feature extraction through iris images using 1-D Gabor filter on different iris datasets. Proceedings of the 2013 Sixth International Conference on Contemporary Computing (IC3), Noida, India.10.1109/IC3.2013.6612236 ↗
18. IIRIS detection for biometric pattern identification using deep learning
19. Chaudhary, A.K., and Pelz, J.B. (2019). Motion tracking of iris features to detect small eye movements. J. Eye Mov. Res., 12.10.16910/jemr.12.6.4 ↗
20. Efficient iris localization and recognition10.1016/j.ijleo.2016.11.150 ↗
21. Ellseg: An ellipse segmentation framework for robust gaze tracking10.1109/TVCG.2021.3067765 ↗
22. Fast iris localization algorithm on noisy images based on conformal geometric algebra10.1016/j.dsp.2020.102682 ↗
23. Iris localization using rough entropy and CSA: A soft computing approach10.1016/j.asoc.2018.02.047 ↗
24. Park, S., Zhang, X., Bulling, A., and Hilliges, O. (2020, January 2–5). Learning to find eye region landmarks for remote gaze estimation in unconstrained settings. Proceedings of the 2018 ACM Symposium on Eye Tracking Research & Applications, Stuttgart, Germany.10.1145/3204493.3204545 ↗
25. Lupu, C., and Turcu, C.O. (2021). Real-Time Iris Recognition of Individuals–an Entrepreneurial Approach. EIRP Proc., 16.
26. Dave, A., and Lekshmi, C.A. (2017, January 22–24). Eye-ball tracking system for motor-free control of mouse pointer. Proceedings of the 2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), Chennai, India.10.1109/WiSPNET.2017.8299921 ↗
27. Human eye pupil detection technique using center of gravity method
28. Image processing based eye detection methods a theoretical review10.11591/eei.v9i3.1783 ↗
29. Real time Face Detection and Optimal Face Mapping for Online Classes10.1088/1742-6596/2161/1/012063 ↗
30. Optical Mouse Sensor for Eye Blink Detection and Pupil Tracking: Application in a Low-Cost Eye-Controlled Pointing Device10.1155/2019/3931713 ↗
31. and Sangal, A.L. (2022). Drowsy Alarm System Based on Face Landmarks Detection Using MediaPipe FaceMesh. Proceedings of First International Conference on Computational Electronics for Wireless Communications, Haryana, India, 11–12 June 2021, Springer.
32. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18–23). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
33. Sifre, L., and Mallat, S. (2014). Rigid-motion scattering for texture classification. arXiv.
34. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv.
35. Aqib Hashmi, S., Chowdhury, R., and Mahdy, D. (2022). Face Detection in Extreme Conditions: A Machine-learning Approach. arXiv.
36. Sarang, P. (2021). Artificial Neural Networks with TensorFlow 2: ANN Architecture Machine Learning Projects, Springer.10.1007/978-1-4842-6150-7 ↗