A Low-Cost Embedded Pupillometry System Enabling Real Time Measurement and On Device Clinical Visualization

Abstract

Pupillometry plays a crucial role in neurological assessments, still the existing automated systems often require very complex setups, heavy offline processing, or expensive and heavy hardware. This paper describes and presents a novel portable pupillometer system that integrates real time image processing with immediate LCD feedback, giving quick outputs, eliminating the need for post processing. The proposed system uses a Raspberry Pi-based architecture that uses the captured infrared images for pupil detection and implements an innovative calibration routine that ensures measurement accuracy across varying conditions. Unlike the traditional systems that store the data and rely on post processing for later analysis, our approach provides instant, calibrated pupil diameter measurements, which are displayed on an integrated LCD screen, making it suitable for point of care calibration corrected measurements. The system can be calibrated multiple times, increasing he accuracy and processes the images at 30 frames per second. The key innovations that the systems provide are: (1) real time calibration corrected measurements, (2) standalone operation without external com putting devices, and (3) immediate visual feedback for clinical decision making. Initial results demonstrate the system’s ability to detect pupil changes suitable for clinical applications that help to detect neurological disorders, intracranial pressure, and evaluate autonomic nervous system functions.

Introduction

The pupillary reflex evaluation is a critical clinical procedure for assessing the physiological activity of the optic nerve, brainstem nuclei, and autonomic pathways. Traditionally measured manually with a penlight and pupil gauge, this method is inexpensive but highly subjective, prone to inter-observer variability, and can miss clinically significant anisocoria, especially in high-pressure environments like ICUs and emergency rooms.

Existing automated pupillometry systems fall into two categories: research-grade systems with high-resolution cameras and advanced processing, and commercial handheld devices like NPi-100/200. While accurate, these systems are costly, require trained personnel, often rely on external devices or proprietary software, and lack flexibility for customization or field deployment.

The proposed work introduces an innovative, Raspberry Pi–based pupillometer that addresses these limitations by providing:

1. Real-time visualization on an integrated LCD screen, eliminating dependence on external computers.

2. Automated calibration to adjust for lighting, camera sensitivity, and alignment, ensuring accurate measurements under varying conditions.

3. Standalone embedded operation using Raspberry Pi 4, handling image acquisition, preprocessing, pupil detection, calibration, and display in a compact, portable system.

4. Open and extensible architecture allowing customization of algorithms, calibration, and integration with EHR systems.

System Design:

• Hardware: Raspberry Pi 4, NoIR infrared camera module, 850 nm IR LED array for non-invasive illumination, LCD display, ergonomic enclosure, and optical alignment mount.

• Software Pipeline: Image acquisition → preprocessing and enhancement → pupil detection → automatic calibration → on-device display.

Methodology:

• Grayscale images captured under infrared lighting minimize pupil constriction and improve contrast.

• Pupil detection uses preprocessing, Gaussian/median filtering, Canny edge detection, contour extraction, and ellipse fitting for precise diameter measurement.

• Automated calibration generates a pixel-to-millimeter conversion, dynamically adjusts for ambient light, and recalibrates as environmental conditions change, ensuring reliable, consistent measurements.

This system offers a portable, affordable, accurate, and real-time pupillometry solution, suitable for clinical, emergency, and research applications, particularly in resource-limited environments.

Conclusion

This paper presented a low cost, feasible Pupillometry system featuring integrated display and automatic calibration. The key innovation immediate presentation of calibrated measurements on an LCD screen, full-filling a significant gap in existing Pupillometry tools by enabling instant clinical decision-making without reliance on external computing infrastructure.

References

[1] M. Bernabei, L. Rovati, L. Peretto, and R. Tinarelli, “A simple portable polychromatic pupillometer for human eye annoyance measurement,” in 2014 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 2014, pp. 1652-1656. [2] H. Hovagimian, C. Walker, D. Granquist-Fraser, and J. Turkovich, “Development of a Remote Pupillometer System for Non-Invasive, Distant Analysis,” in 2012 Northeast Bioengineering Conference, 2012, pp. 153-154. [3] D. Couret et al., “Reliability of standard pupillometry practice in neu- rocritical care: an observational, double-blinded study,” Critical Care, vol. 20, no. 1, pp. 5-8, 2016. [4] R. Kerr et al., “Underestimation of Pupil Size by Critical Care and Neurosurgical Nurses,” American Journal of Critical Care, vol. 25, no. 3, pp. 213-219, 2016. [5] M. P. Bindiganavale and H. E. Moss, “Development and Implementation of a Handheld Pupillometer for Detection of Optic Neuropathies,” Current Eye Research, 2021. [6] R. G. Garcia et al., “Automated Pupillometer Using Edge Detection in OpenCV for Pupil Size and Reactivity Assessment,” in 2019 3rd International Conference on Imaging, Signal Processing and Communication, 2019, pp. 143-149. [7] NeurOptics, “NPi-200 Pupillometer System,” [Online]. Available: https://neuroptics.com/npi-200-pupillometer. [Accessed: 12-Jan-2026]. [8] L. M. Chen et al., “Inter-rater reliability in pupil size measurement,” Journal of Clinical Neuroscience, vol. 19, no. 6, pp. 867-871, 2012. [9] S. Mathoˆt, “Pupillometry: Psychology, Physiology, and Function,” Jour- nal of Cognition, vol. 1, no. 1, pp. 1-23, 2018. [10] M. A. Khan, K. Salah, and A. Kumar, “Raspberry Pi based low-cost portable image processing system for biomedical applications,” IEEE Access, vol. 8, pp. 64950-64960, 2020. [11] T. Larson and W. Bauer, “Infrared imaging for medical applications: A review,” Journal of Medical Systems, vol. 43, no. 8, pp. 241-248, 2019. [12] P. Johnson et al., “Real-time image acquisition techniques for embedded vision systems,” IEEE Transactions on Embedded Computing Systems, vol. 17, no. 4, pp. 892-905, 2018. [13] S. Zhang and M. Li, “Adaptive image preprocessing for pupil detection under variable lighting,” Biomedical Signal Processing and Control, vol. 52, pp. 342-351, 2019. [14] J. Canny, “A computational approach to edge detection,” IEEE Trans- actions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679-698, 1986. [15] W. Patil, S. Sorte, P. Daigavane, S. Joshi, and P. Ghutke, “Detection and Screening of the Neovascularization Diabetic Retinopathy by an Automated System Caused Due to Diabetes,” in Proceedings of International Conference on Data Analytics and Insights, ICDAI 2023, 2023, pp. 319–330. [16] K. A. Dhone, S. Joshi, and S. Sonaskar, “IoT-SyringeX: A Cutting-Edge Solution for Automated Injection Pumps,” in Innovations in Electrical and Electronic Engineering, 2024, pp. 633–645. [17] C. Series, “Next-Gen Medical Technology a Smart Approach to Syringe Injection Pump Automation Next-Gen Medical Technology a Smart Approach to Syringe Injection Pump Automation,” 2024, doi: 10.1088/1742-6596/2763/1/012028. [18] O. Access, “Improving Accuracy of Classification of Emotions Using EEG Signal and Adaptive PSO Improving Accuracy of Classification of Emotions Using EEG Signal and Adaptive PSO,” 2021, doi: 10.1088/1757-899X/1170/1/012013. [19] P. Bagde, S. Joshi, S. Dorle, P. Ghutke, W. Patil, and M. Chakole, “Optimizing X-Band Low Noise Amplifier: Design Challenges, Topologies and Technological Insights,” in 2024 2nd International Conference on Emerging Trends in Engineering and Medical Sciences (ICETEMS), 2024, pp. 850–855. doi: 10.1109/ICETEMS64039.2024.10965066. [20] S. Borkar, P. Ghutke, W. Patil, S. Joshi, and S. Sorte, “Advancing Pharmaceutical Manufacturing Through Delta Robot Fabrication,” in 2023 IEEE 5th International Conference on Cybernetics, Cognition and Machine Learning Applications (ICCCMLA), 2023, pp. 269–274. doi: 10.1109/ICCCMLA58983.2023.10346873. [21] A. Nimje, S. Joshi, and P. Ghutke, “PiChrono: Developing an Affordable 3-in-1 Timekeeping Device using Raspberry Pi,” in 2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC), 2023, pp. 268–275. doi: 10.1109/ICESC57686.2023.10193653. [22] A. Gawaikar, S. Sorte, P. Ghutke, W. Patil, and S. Joshi, “Review of Da Vinci Surgical System and Haptic Feedback Device for Telesurgery,” in 2023 8th International Conference on Communication and Electronics Systems (ICCES), 2023, pp. 1596–1600. doi: 10.1109/ICCES57224.2023.10192689. [23] D. Raipure, D. Padole, S. Joshi, W. Patil, S. Patil, and A. Dodke, “Design of Non Stop Solar Electric Vehicle Charging System Using Inductive Charging System-A Review,” in 2024 International Conference on IoT Based Control Networks and Intelligent Systems (ICICNIS), 2024, pp. 744–751. doi: 10.1109/ICICNIS64247.2024.10823283. [24] V. Meshram, S. Patil, V. Bora, W. Patil, P. Ghutke, and S. Joshi, “Design and Optimization of RF Self Biased Ku Band LNA with Low Noise, High Gain,” in 2025 International Conference on Emerging Smart Computing and Informatics (ESCI), 2025, pp. 1–5. doi: 10.1109/ESCI63694.2025.10987975. [25] D. Raipure, W. Patil, D. Padole, S. Joshi, L. Thakre, and P. Ghutke, “Implementation of Photovoltaic Based EV Charging System Using Inductive Charging System,” in 2025 6th International Conference on Data Intelligence and Cognitive Informatics (ICDICI), 2025, pp. 890–895. doi: 10.1109/ICDICI66477.2025.11135118. [26] V. Taywade, P. Ghutke, P. Gade, S. Joshi, W. Patil, and L. Thakre, “A Low-Voltage Low-Power CMOS OTA Using Body-Driven Topology for Biomedical Applications,” in 2025 12th International Conference on Emerging Trends in Engineering & Technology - Signal and Information Processing (ICETET - SIP), 2025, pp. 1–6. doi: 10.1109/ICETETSIP64213.2025.11156199. [27] M. Khanapurkar, T. Khatavkar, K. Akant, S. Joshi, P. M. Potdar, and M. Atre, “Implementation of Learner Generated MOOC Through Inter-Institute Faculty - Student Peer Collaboration,” in 2022 IEEE Global Engineering Education Conference (EDUCON), 2022, pp. 597–602. doi: 10.1109/EDUCON52537.2022.9766763. [28] S. Borkar, P. Ghutke, W. Patil, S. Joshi, and S. Sorte, “A Review of Pick and Place Robots for the Pharmaceutical Industry,” in 2023 11th International Conference on Emerging Trends in Engineering & Technology - Signal and Information Processing (ICETET - SIP), 2023, pp. 1–6. doi: 10.1109/ICETET-SIP58143.2023.10151652. [29] A. Nimje, S. Joshi, P. Ghutke, W. Patil, and S. Sorte, “RasPiChrono: A Raspberry Pi Based Economical 3-in-1 Countdown Timer,” in 2023 11th International Conference on Emerging Trends in Engineering & Technology - Signal and Information Processing (ICETET - SIP), 2023, pp. 1–6. doi: 10.1109/ICETET-SIP58143.2023.10151479. [30] V. Meshram, S. Patil, V. Bora, W. Patil, P. Ghutke, and S. Joshi, “A Paper of RF Low Noise Amplifier Using Ku Band,” in 2024 International Conference on Integrated Intelligence and Communication Systems (ICIICS), 2024, pp. 1–7. doi: 10.1109/ICIICS63763.2024.10859341.

Copyright

Copyright © 2026 Mr. Shahu Ingole, Dr. Sonali Joshi, Dr. Kapil Jajulwar, Dr. Sujesh Ghodmare, Dr. Nilesh Nirwan, Dr. Payal Ghutke. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.