CFP last date
22 April 2024
Reseach Article

Comparison of Detection Accuracy and Effect of JPEG2000 Compression on Iris Recognition

by Prashant Kapoor, Paresh Rawat
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 162 - Number 4
Year of Publication: 2017
Authors: Prashant Kapoor, Paresh Rawat
10.5120/ijca2017913281

Prashant Kapoor, Paresh Rawat . Comparison of Detection Accuracy and Effect of JPEG2000 Compression on Iris Recognition. International Journal of Computer Applications. 162, 4 ( Mar 2017), 37-42. DOI=10.5120/ijca2017913281

@article{ 10.5120/ijca2017913281,
author = { Prashant Kapoor, Paresh Rawat },
title = { Comparison of Detection Accuracy and Effect of JPEG2000 Compression on Iris Recognition },
journal = { International Journal of Computer Applications },
issue_date = { Mar 2017 },
volume = { 162 },
number = { 4 },
month = { Mar },
year = { 2017 },
issn = { 0975-8887 },
pages = { 37-42 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume162/number4/27235-2017913281/ },
doi = { 10.5120/ijca2017913281 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:08:07.407989+05:30
%A Prashant Kapoor
%A Paresh Rawat
%T Comparison of Detection Accuracy and Effect of JPEG2000 Compression on Iris Recognition
%J International Journal of Computer Applications
%@ 0975-8887
%V 162
%N 4
%P 37-42
%D 2017
%I Foundation of Computer Science (FCS), NY, USA
Abstract

In today's digital world, identification based on biometrics has received much attention from research community as well as from industries for security applications. Iris recognition is evolving as one of the most active techniques in biometrics technology accounting to its high reliability for identification and is proved to be most error free means to identify persons. Iris is considered as the reliable biometric feature based on its uniqueness and robustness. To perform iris recognition iris/eye image is captured from numerous person's and these images should be stored in the data base & retrieved whenever required. Hence there is need of huge databases of iris images. Compression is a unique option available if available storage space is not sufficient for the images. Compression empowers a reduction in the space needed to store these iris images. The aim of this paper is to present the effects of iris image compression on the recognition performance. Usually iris images are 600 times bigger than the Iris Code templates which requires enormous space for storage. It is expected that iris data should be secured, transmitted and embedded in media in the form of images instead of templates. To obtain this objective considering its implications for bandwidth and storage, this paper presents the scheme that combine ROI(region-of-interest) isolation with JPEG 2000 compression at different levels using publicly available database of iris images each in case of two cases of Normalized iris images on with classic Daughman's rubber sheet model and the second one through non-linear Biomechanical model. It is concluded that JPEG 2000 compression gives the better results with iris images normalized with Biomechanical model with minimum impact on recognition performance.

References
  1. I.J Shaikh, S.M Mukane, The Effect of Iris Image Compression on Recognition Performance published in International Journal of Computer Applications (0975 – 8887) Volume 113 – No. 18, March 2015
  2. A.P. Bradley and F.W.M. Stentiford, “JPEG2000 and region of interest coding,” Digital Imaging Computing Techniques and Applications, Melbourne, 2002. Available at: http://www.ee.ucl.ac.uk/ fstentif/DICTA02.p
  3. Brian C. Smith, Lawrence A. Rowe, Compressed Domain Processing of JPEG-encoded images.pdf,International Journal of Computer Applications (0975 - 8887) Volume 65 - No. 04, September 2015
  4. MajidRabbani, Rajan Joshi, An overview of the JPEG2000 still image compression standard, Signal Processing: Image Communication 17 (2002) 3–48,Elsevier volume 48, 2014
  5. Robert Buckley, Using Lossy JPEG 2000 Compression For Archival Master Files.pdf, Prime Contract/Solicitation No.: LCOSI10T0057 Prime Task Order No. OSI12T0010, March, 2013
  6. Michael W. Marcellin, Michael J. Gormish, Ali Bilgin1, Martin P. Boliek, An Overview of JPEG-2000.pdf,IEEE Data Compression Conference, pp. 523-541, 2015
  7. RituChourasiya and Prof. AjitShrivastava, a study of image compression based transmission algorithm using spihtforlow bit rate application.pdf, Advanced Computing: An International Journal ( ACIJ ), Vol.3, No.6, November 2012
  8. SwethaDodla, Y David SolmonRaju, K V Murali Mohan, Image Compression using Wavelet and SPIHT Encoding Scheme, International Journal of Engineering Trends and Technology (IJETT) – Volume 4 Issue 9- Sep 2013
  9. Mascher-Kampfer, Herbert St¨ogner, and Andreas Uhl1,Comparison of Compression Algorithms’ Impact on Fingerprint and Face Recognition Accuracy. pdf, International Journal of Engineering Trends and Technology (IJETT) – Volume 4 Issue 9- Sep 2015
  10. Hannes Hartenstein, Associate Member, IEEE, Matthias Ruhl, and DietmarSaupe, Region-Based Fractal Image Compression, IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 9, NO. 7, JULY 2015
  11. Alphones Maria, Amlu Anna Joshy, Aneeta Christopher, Anjali B4, RanjithaRajan, Iris Database Compression Using Haar Wavelet Decomposition and Huffman Coding, International Journal of Advanced Research in Computer and Communication Engineering Vol. 5, Issue 4, April 2016
  12. MayankVatsa , Richa Singh, P .Gupta, Improving Iris Recognition Performance Using Segmentation, Quality Enhancement, Match Score Fusion, and Indexing
  13. A.K.Jain,A.Ross,andS.Pankanti,"Biometrics:ATool for Information Security", IEEE Transactions on InformationForensicsandSecurity,Vol.1,No.2,2006,pp. 125-143.
  14. V.Dorairaj,A. Schmid, and G. Fahmy,"Performance Evaluation of Iris Based RecognitionSystemImplementing PCAandICAEncodingTechniques",inProceedings of SPIE,2005,pp.51-58.
  15. S.Shah,andA.Ross,"IrisSegmentationUsingGeodesic Active Contours", IEEE Trans. on InformationForensics andSecurity,Vol.4,No.4,2009,pp.824-836.
  16. I.JShaikh, S.M Mukane, The Effect of Iris Image Compression on Recognition Performance published in International Journal of Computer Applications (0975 – 8887) Volume 113 – No. 18, March 2015
  17. A.P. Bradley and F.W.M. Stentiford, “JPEG2000 and region of interest coding,” Digital Imaging ComputingTechniques and Applications, Melbourne, 2002. Available at: http://www.ee.ucl.ac.uk/fstentif/DICTA02.p
  18. Surjeet Singh, Kulbir Singh, Segmentation Techniques for Iris Recognition System,Iinternational Journal of Scientific & Engineering Res V volume 2, Issue 4, April
  19. J. Daugman. How iris recognition works. Proceedings of nternational Conference on Image Processing, Vol. 1, 2002.
  20. A.M.Raid, W.M.Khedr, M. A. El-dosuky and Wesam Ahmed, Jpeg Image Compression Using Discrete CosineTransform.pdf - A Survey, International Journal of Computer Science & Engineering Survey (IJCSES) Vol.5, No.2, April 2014
Index Terms

Computer Science
Information Sciences

Keywords

Biometric Iris Detection Security purpose Recognition Performance compression Matching.