Abstract
The pupil detection algorithm plays a key role in the non-contact tono-meter, auto ref-keratometry and optical coherence tomography in medical ophthalmology diagnostic equipment. A major challenge associated with pupil detection techniques is the use of conventional neural networks based on algorithms, integro-differential operator and circular hough transform, which leads to inefficient use of hardware resources in FPGA. To overcome this, using an average black pixel density technique, the proposed human eye pupil detection system is used to easily recognize and diagnose the human eye pupil area. Double threshold, logical OR, morphological closing and average black pixel density modules are involved in the proposed solution. To test the proposed method, the near infrared (NIR) iris databases are being used, namely: CASIA-IrisV4 and IIT Delhi and have achieved 98% percent accuracy, specificity, sensitivity. The proposed work was synthesized via Zynq XC7Z020 FPGA and the results are compared with previous approaches.
Similar content being viewed by others
Abbreviations
- BRAM:
-
Block RAM
- CASIA:
-
Chinese academy of science research institute of automation
- CHT:
-
Circular hough transform
- CNN:
-
Conventional neural network
- DDR:
-
Double data rate
- FPGA:
-
Field programmable gate array
- FCN:
-
Fully connected neural network
- f logical or :
-
Unwanted black pixel removed image
- f morpclose :
-
Morphological closed image
- FP:
-
False positive
- FN:
-
False negative
- HT:
-
Hough transforms
- IIT:
-
Indian Institute of Technology
- IDO:
-
Integro differential operator
- LT:
-
Logarithmic transformation
- LUT:
-
Look up table
- PLT:
-
Power law transformation
- TP:
-
True positive
- TN:
-
True negative
References
Vineet K, Asati A and Gupta A 2017 Hardware implementation of a novel edge-map generation technique for pupil detection in NIR images. Eng. Sci. Technol. Int. J. 20(4): 694–704
Khalighi S, Pak F and Tirdad P 2015 Iris recognition using robust localization and nonsubsampled contourlet based features. J. Signal Process. Syst. 81: 111–128
Farmanullah J, Imran U, Shahid A and Shahzad A 2014 A dynamic non-circular iris localization technique for non-ideal data. Comput. Electr. Eng. 40: 215–226
Javadi A H, Hakimi Z, Barati M, Walsh V and Tcheang L 2015 SET: a pupil detection method using sinusoidal approximation features. Front. Neuroeng. 8: 1–10
Swirski L, Bulling A and Dodgson N 2012 Robust real-time pupil tracking in highly off-axis images Eye Tracking Research and Applications Symposium (ETRA). 173–176
Gwon S Y, Lee C, Eui L, Park W and Kang 2013 Robust eye and pupil detection method for gaze tracking. Int. J. Adv. Robot. Syst. 10: 98–105
Mingxin Y, Yingzi L, David S and Guo Y 2015 An easy iris center detection method for eye gaze tracking system. J. Eye Movement Res. 8: 1–20
Ryan W, Woodard D, Duchowski, A and Birchfield S 2008 Adapting starburst for elliptical iris segmentation In: Proceedings of the 2nd IEEE International Conference on Biometrics: Theory, Applications and Systems. 1 – 7
Arsalan M, Rizwan N, Ganbayar Y, Kang H and Ryoung P 2018 Deep learning-based gaze detection system for automobile drivers using a NIR Camera Sensor. Sensors 18(2): 456–490
Ramlee R A and Noah Z M 2017 Pupil segmentation of abnormal eye using image enhancement in spatial domain. IOP Conf. Ser.: Mater. Sci. Eng. 210: 012031
Elhossini A, Moussa M 2012 Memory efficient FPGA implementation of hough transform for line and circle detection. Canadian conference on Electrical and Computer Engineering. 1–5
Nosrati M and Karimi R 2011 Detection of circular shapes from impulse noisy images using median and laplacian filter and circular hough transform In: 8th International Conference on Electrical Engineering, Computing Science and Automatic Control. 1–5
Hokchhay T, Heng Z and Sherief R 2019 A resource-efficient embedded iris recognition system using FCNs. ACM J. Emerg. Technol. Comput. Syst. 16: 1–23
Liu Y, Derman C E, Calderoni G and Bahar R I 2020 Hardware acceleration of robot scene perception algorithms IEEE/ACM International Conference On Computer Aided Design (ICCAD). 1–8
CASIA-Iris database V4 [Online]. Available: http://www.cbsr.ia.ac.cn/china/Iris%20Databases%20CH.asp
The IIT Delhi Iris Database. Available: https://www4.comp.polyu.edu.hk/~csajaykr/IITD/Database_Iris.html
Fernando A F and Josef B 2012 Iris boundaries segmentation using the generalized structure tensor. A study on the effects of image degradation In: Proceedings of the IEEE International Conference on Biometrics: Theory, Applications, and Systems. 426–431
Nadia O, Garcia B, Sonia S and Dorizzi, 2015 OSIRIS: an open source iris recognition software. Pattern Recognit. Lett. 82(2): 124–131
Uhl A and Wild P 2012 Weighted adaptive hough and ellipso polar transforms for real-time iris segmentation In Proceedings of the IEEE International Conference on Biometrics. 283–290
Rathgeb C, Uhl A and Wild P 2013 Iris biometrics: from segmentation to template security USA. Springer
Masek L and Kovesi P 2003 Recognition of human iris patterns for biometric identification M.S. dissertation, School of Computer Science and Software Engineering, University of West Australia, Perth, Australia
Gangwar A, Joshi A, Singh A and Alonso F 2018 Irisseg: a fast and robust iris segmentation framework for non-ideal iris images In: Proceedings of the IEEE International Conference on Biometrics.1–8
Hashemi S, Anthony N, Tann H, Bahar R and Reda S 2017 Understanding the impact of precision quantization on the accuracy and energy of neural networks In: Proceedings of the IEEE Design, Automation, and Test in Europe Conference and Exhibition. 1474–1479
Arsalan M, Rizwan N, Kim D S, Nguyen P Ha and Owais M 2018 Irisdensenet: robust iris segmentation using densely connected fully convolutional networks in the images by visible light and near-infrared light camera sensors Sensor. 18(5): 1501-1521
Ngo H, Rakvic R, Broussard R and Ives R 2014 Resource-aware architecture design and implementation of hough transform for a real-time iris boundary detection system. IEEE Trans. Consum. Electron. 60: 485–492
Vineet K, Asati A and Gupta A 2016 Iris localization in iris recognition system: algorithms and hardware implementation Ph.D. dissertations Birla Institute of Technology and Science India
Avey J 2018 An FPGA-based hardware accelerator for iris segmentation, Ph.D. dissertations Iowa State University Iowa
Lee W L, Hyeonchang C, Chul G, Park S and Kang L 2012 Auto-focusing method for remote gaze tracking camera. Opt. Eng. 51(6): 063204
Cho C L, Kwang L, Eui C P, Kang L, Heekyung C and Jihun 2012 Gaze detection by wearable eye-tracking and NIR LED-based head-tracking device based on SVR. ETRI Journal. 34(4): 542–552
Fuhl W, Tonsen M, Andreas K and Enkelejda 2016 Pupil detection for head-mounted eye tracking in the wild: an evaluation of the state of the art. Mach. Vis. Appl. 27: 1275–1288
Mestre C, Josselin G and Jaume P 2018 Robust eye tracking based on multiple corneal reflections for clinical applications. J. Biomed. Opt. 23(3): 1–9
Brousseau B R, Jonathan E and Moshe 2018 Accurate model-based point of gaze estimation on mobile devices. Vision 2(3): 35
Acknowledgement
The authors thank the Chinese Academy of Science Research Institute of Automation (CASIA) and IIT Delhi for accessing their image datasets.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
NAVANEETHAN, S., NANDHAGOPAL, N. RE-PUPIL: resource efficient pupil detection system using the technique of average black pixel density. Sādhanā 46, 114 (2021). https://doi.org/10.1007/s12046-021-01644-x
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12046-021-01644-x