Abstract
Newly introduced Iris recognition systems (IRSs) run on serial processors. In this paper, an alternative method has been introduced for parallel processing on Graphic processing unit (GPU) with Compute unified device architecture (CUDA) in order to increase the speed of the system. The IRS has two main parallel processing criteria, which include the division of computations into hundreds of independent units and the time of calculation more than the time of transferring from the GPU. The IRS is divided into six stages including imaging, pre-processing, segmentation, normalization, feature extraction, and matching. In order to increase speed and accuracy, two stages of iris segmentation and matching play an important role in the IRS. In this paper parallel execution of an identical algorithm for these two stages has been used. The reason for paralleling the iris segmentation stage and their low speed matching is due to a great amount of information in the iris database, plenty of calculations and lack of data dependency in these two stages. For parallelism at the segmentation stage, for each radius, the Hough transform (HT) is a processor, and in the matching stage two parts are considered: The first part consists of 32 actions comparing the input code with the database code in parallel and in the second part 2048 bits with the use of threads on each processor is performed in two sub-sections in pairs of bits and in parallel with each other. Finally, the two-way coding is achieved. In compare of existing methods, this method has rather more accurate and is also superior in terms of processing time on the GPU with CUDA. The results of the implementation of the above method on the images in UBIRIS, BATH, CASIA and MMUI databases show that the proposed method has a precision accuracy of 99.12%, 97.98%, 98.80% and 98.34%, respectively, and the average speedup for parallel processing of images in the database in the proposed method on the GPU with CUDA are 18.8, 14.7, 18, and 19 times, respectively.
Similar content being viewed by others
References
Abikoye Oluwakemi C, Sadiku J, Adewole Kayode S, Jimoh Rasheed G (2014) Iris feature extraction for personal identification using fast wavelet transform (FWT). Int J Appl Inf Syst 6:1–6
Al-Waisy AS, Qahwaji R, Ipson S, Al-Fahdawi S, Nagem TM (2018) A multi-biometric iris recognition system based on a deep learning approach. Pattern Anal Appl 21:783–802
Ambraa PD, Filippone S (2016) A parallel generalized relaxation method for high-performance image segmentation on GPUs. J Comput Appl Math 13:35–44
Arsalan M, Kim DS, Lee MB, Owais M, Park KR (2019) FRED-net: fully residual encoder-decoder network for accurate iris segmentation. Exp Syst Appl 122:217–241
Bath iris image database. http://www.smartsensors.co.uk/products
Bazrafkan S, Thavalengal S, Corcoran P (2018) An end to end deep neural network for iris segmentation in unconstrained scenarios. Neural Netw 106:79–95
Cappelli R, Ferrara M, Maltoni D (2015) Large-scale fingerprint identification on GPU. Inf Sci 306:1–20
CASIA-IrisV3 Interval database. http://www.cbsr.ia.ac.cn/english/iris-database.asp
Daugman J (2007) New methods in iris recognition. IEEE Trans Syst Man Cybern 37:1167–1175
De A, Zhang Y, Guo C (2016) A parallel adaptive segmentation method based on SOM and GPU with application to MRI image processing. Neurocomputing 198:180–189
Eklund A, Dufort P, Forsberg D, LaConte SM (2013) Medical image processing on the GPU—past, present and future. Med Image Anal 17:1073–1094
Feng C, Zhao D, Huang M (2015) Image segmentation using CUDA accelerated non-local means denoising and bias correction embedded fuzzy c-means (BCEFCM). Signal Process 11:487–513
Goceri E (2015) Effects of chosen scalar products on gradient descent algorithms. In: The 28th international conference of the Jangjeon mathematical society (ICJMS), pp 70–75
Goceri E (2016) Fully automated liver segmentation using sobolev gradient-based level set evolution. Int J Numer Methods Biomed Eng 32(11)
Goceri E (2017a) Future healthcare: will digital data lead to better care? In: 4th world conference on health sciences (HSCI2017), pp 7–11
Goceri E (2017b) Intensity normalization in brain MR images using spatially varying distribution matching. In: Proceeding of the international conference on conferences graphics, visualization, computer vision and image processing (CGVCVIP 2017), pp 300–304
Goceri E (2017c) Fully automated and adaptive intensity normalization using statistical features for brain MR images. Celal Bayar Univ J Sci 14(1):125–134
Goceri E (2018) Formulas behind deep learning success. In: International conference on applied analysis and mathematical modeling (ICAAMM2018), pp 156-162
Goceri E (2019) Diagnosis of alzheimer’s disease with sobolev gradient based optimization and 3D convolutional neural network. Int J Numer Methods Biomed Eng 35:1–16
Goceri E, Goceri N (2017) Deep learning in medical image analysis: recent advances and future trends. In: 11th international conference on computer graphics, visualization, computer vision and image processing (CGVCVIP 2017), pp 305–310
Goceri E, Gooya A (2018) On the importance of batch size for deep learning. In: International conference on mathematics (ICOMATH2018), pp 99–105
Goceri E, Martinez ED (2014) A level set method with sobolev gradient and haralick edge detection. In: The 4th world conference on information technology, (WCIT2013), vol 5, pp 131–140
Goceri E, Songul C (2018) Biomedical information technology: image based computer aided diagnosis systems. In: International conference on advanced technologies, pp 132–138
Goceri E, Goksel B, Elder JB, Puduvalli VK, Otero JJ, Gurcan MN (2017) Quantitative validation of anti-PTBP1 antibody for diagnostic neuropathology use: image analysis approach. Int J Numer Methods Biomed Eng 33(11):1–14
Happ PN, Feitosa RQ, Bentes C, Farias R (2013) A region growing segmentation algorithms for GPUs. Int Res Rep 30:73–94
Huqqani AA, Schikuta E, Ye S, Chen P (2013) Multicore and GPU parallelization of neural networks for face recognition. In: International conference on computational science (ICCS 2013), vol 18, pp 349–358
Jain V, Patel D (2016) A GPU based implementation of robust face detection system. Proc Comput Sci 87:156–163
Jan F, Usman I, Agha S (2013) Reliable iris localization using Hough transform. Histogram-bisection and eccentricity. Springer Signal Process 93:230–241
Lastra M, Caraba J, Gutierrez D, Benitez JM, Herrera F (2015) Fast fingerprint identification using GPUs. Inf Sci 13:195–214
Ma L, Tan T, Wang Y, Zhang M (2004) Efficient iris recognition by characterizing key local variations. IEEE Trans Image Process 13:739–750
Mahlouji M, Noruzi A (2012) Human iris segmentation for iris recognition in unconstrained environments. IJCSI Int J Comput Sci 9:149–155
MMU1 and MMU2 iris databases. http://pesona.mmu.edu.my/ccteo
Noruzi A, Mahlouji M, Shahidinejad A (2019) Robust iris recognition in unconstrained environments. J Artificial Intell Data Mining. https://doi.org/10.22044/JADM.2019.7434.1884
Ouabida E, Essadique A, Bouzid A (2017) Vander lugt correlator based active contours for iris segmentation and tracking. Expert Syst Appl 71:383–395
Radman A, Zainal N, Suandi S (2017) Automated segmentation of iris images acquired in an unconstrained environment using HOG-SVM and GrowCut. J Dig Signal Process 64:60–70
Roy K, Bahattacharya P, Suen CY (2011) Iris recognition using shape-guided approach and game theory. Pattern Anal Appl 14:329–348
Sakr FZ, Taher M, El-Bialy M, Wahba AM (2012) Accelerating iris recognition algorithms on GPUs. In: Cairo international biomedical engineering conference, pp 73–76
Sakr FZ, Taher M, Wahba AM (2011) High Performance iris recognition system on GPU. In: International conference on computer engineering and systems (ICCES), pp 237–242
Sardar M, Mitra S, Shankar BU (2018) Iris localization using rough entropy and CSA: a soft computing approach. Appl Soft Comput 67:61–69
Tan CW, Kumar A (2012) Efficient iris segmentation using grow-cut algorithm for remotely acquired iris images. In: 5th IEEE international conference on biometrics: theory. applications and systems (BTAS), vol 12, pp 99–104
UBIRIS dataset obtained from Department of Computer Science, University of Beira Interior, Portugal. http://iris.di.ubi.pt
Umer S, Dhara BC, Chanda B (2017) Texture code matrix-based multi-instance iris recognition. Pattern Anal Appl 19:283–295
Vandal NA, Savvides M (2010) CUDA accelerated iris template matching on Graphics Processing Units (GPUs). Biometrics Compendium, IEEE, pp 130–138
Zhao Z, Kumar A (2019) A deep learning based unified framework to detect, segment and recognize irises using spatially corresponding features. Pattern Recognit Lett 93:546–557
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Noruzi, A., Mahlouji, M. & Shahidinejad, A. Iris recognition in unconstrained environment on graphic processing units with CUDA. Artif Intell Rev 53, 3705–3729 (2020). https://doi.org/10.1007/s10462-019-09776-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-019-09776-7