access icon free Super resolution and recognition of long range captured multi-frame iris images

© The Institution of Engineering and Technology
Received 31/05/2016, Accepted 05/01/2017, Revised 10/12/2016, Published 10/01/2017

In this study, a framework to super resolve and recognise the long range captured iris polar images is proposed. The proposed framework consists of best frame selection algorithm, modified diamond search algorithm, Gaussian process regression (GPR) based and enhanced iterated back projection (EIBP)-based super-resolution approach, fuzzy entropy-based feature selector and neural network (NN) classifier. The framework uses linear kernel co-variance function in local patch-based GPR and EIBP algorithms and it super resolves the iris images depending on the contents of the patches, without an external dataset. NN classifier classifies the iris images by using features extracted using discrete cosine transform domain based no-reference image quality assessment model, Gray level co-occurrence matrix, Hu seven moments and statistical features. The framework is tested using CASIA long range iris database by comparing and analysing the peak signal-to-noise ratio, structural similarity index matrix and visual information fidelity in pixel domain of proposed algorithms with Yang and Nguyen framework. The results demonstrate that the proposed framework is well suited for recognition of iris images captured at a long distance.

Inspec keywords: matrix algebra; Gaussian processes; search problems; visual databases; fuzzy set theory; feature extraction; neural nets; image resolution; regression analysis; entropy

Other keywords: EIBP algorithms; local patch-based GPR algorithms; discrete cosine transform domain; peak signal-to-noise ratio; statistical features; Hu seven moments; linear kernel covariance function; feature extraction; Nguyen framework; no-reference image quality assessment model; CASIA long range iris database; super-resolution approach; structural similarity index matrix; gray level co-occurrence matrix; best frame selection algorithm; Yang framework; DCT; long range captured multiframe iris image recognition; enhanced iterated back projection; fuzzy entropy-based feature selector; neural network classifier; pixel domain; modified diamond search algorithm; visual information fidelity; Gaussian process regression; NN classifier

Subjects: Other topics in statistics; Optimisation techniques; Algebra; Combinatorial mathematics; Image recognition; Other topics in statistics; Neural computing techniques; Computer vision and image processing techniques; Combinatorial mathematics; Algebra; Optimisation techniques; Spatial and pictorial databases

References

    1. 1)
      • 40. Wang, : ‘Image quality assessment: from error visibility to structural similarity’. IEEE Proc. on Image Processing, 2004.
    2. 2)
      • 2. Chaudhuri, S.: ‘Super resolution imaging’ (Kluwer Academic Publishers, 2002).
    3. 3)
      • 20. Deshpande, A., Patavardhan, P.: ‘Segmentation and quality analysis of long range captured iris image’, ICTACT J. Image Video Process., 2016, 6, pp. 1280–1283.
    4. 4)
      • 8. Wang, L., Meng, G., Wu, H., et al: ‘Edge-directed single-image super-resolution via adaptive gradient magnitude self-interpolation’, IEEE Trans. Circuits Syst. Video Technol., 2013, 23, pp. 1289–1299.
    5. 5)
      • 4. Kohler, T., Brost, A., Mogalle, K., et al: ‘Multi-frame super-resolution with quality self-assessment for retinal fundus videos’, Med. Image Comput. Comput.-Assist. Interv., 2014, 8673, pp. 650–657.
    6. 6)
      • 10. Gao, X., Wang, Q., Li, X., et al: ‘Zernike-moment-based image super resolution’, IEEE Trans. Image Process., 2011, 20, pp. 2738–47.
    7. 7)
      • 23. Jia, H.: ‘A new cross diamond search algorithm for block motion estimation’. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 2004.
    8. 8)
      • 18. Park, U., Jillela, R.R., Ross, A., et al: ‘Periocular biometrics in the visible spectrum’, IEEE Trans. Inf. Forensics Secur., 2011, 6, pp. 96–106.
    9. 9)
      • 24. Haghighat, , Aghagolzadeha, A., Seyedarabia, H., et al: ‘Multi-focus image fusion for visual sensor networks in DCT domain’, Comput. Electr. Eng., 2011, 37, pp. 789–797.
    10. 10)
      • 19. Viola, P.: ‘Rapid object detection using a boosted cascade of simple features’. IEEE Conf. on Computer Vision and Pattern Recognition, 2001.
    11. 11)
      • 38. Yang, J., Wang, Z., Lin, Z., et al: ‘Coupled dictionary training for image super-resolution’, IEEE Trans. Image Process., 2012, 21, pp. 3467–3478.
    12. 12)
      • 43. Zhou, : ‘Evaluating the quality of super-resolved images for face recognition’. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2008.
    13. 13)
      • 34. Shie, J.-D., Chen, S.-M.: ‘Feature subset selection based on fuzzy entropy measures for handling classification problems’, Springer Appl. Intell., 2008, 28, pp. 69–82.
    14. 14)
      • 30. Haralick, R.M., Shanmugam, K., Dinstein, I., et al: ‘Textural features for image classification’, IEEE Trans. Syst. Man Cybern., 1973, 3, pp. 610–621.
    15. 15)
      • 28. Saad, M.A.: ‘DCT statistics model-based blind image quality assessment’. IEEE Int. Conf. on Image Processing, 2011.
    16. 16)
      • 39. Thanh, N., Sridharan, S., Denman, S., et al: ‘Feature-domain super-resolution framework for Gabor-based face and iris recognition’. IEEE Int. Conf. in Computer Vision and Pattern Recognition, 2012.
    17. 17)
      • 11. Zhang, K., Gao, X., Tao, D., et al: ‘Single image super-resolution with multiscale similarity learning’, IEEE Trans. Neural Netw. Learn. Syst., 2013, 24, pp. 1648–59.
    18. 18)
      • 16. Shin, K.Y., Park, K.R., Kang, B.J., et al: ‘Super-resolution method based on multiple multi-layer perceptrons for iris recognition’. Int. Conf. on Ubiquitous Information Technologies Applications, 2009.
    19. 19)
      • 5. Tam, W.S., Kok, C.W., Siu, W.C.: ‘Modified edge-directed interpolation for images’, J. Electron. Imaging, 2010, 19, (1), pp. 1–20, Article ID 013011.
    20. 20)
      • 14. Wang, N., Tao, D., Gao, X., et al: ‘Comprehensive survey to face hallucination’, Int. J. Comput. Vis., 2014, 106, pp. 9–30.
    21. 21)
      • 29. Huan, J., Parris, M., Lee, J., et al: ‘Scalable FPGA-based architecture for DCT computation using dynamic partial reconfiguration’, ACM Trans. Embed. Comput. Syst., 2009, 9, pp. 1–18.
    22. 22)
      • 3. Park, S., Park, M.K., Kang, M.G., et al: ‘Super-resolution image reconstruction: technical overview’, IEEE Signal Process. Mag., 2003, 20, pp. 21–36.
    23. 23)
      • 27. Irani, M.: ‘Super resolution from image sequences’. IEEE Conf. on Pattern Recognition, 1990.
    24. 24)
      • 37. CASIA Iris Image Database, http://biometrics.idealtest.org/’.
    25. 25)
      • 12. Fahmy, G.: ‘Super-resolution construction of iris images from a visual low resolution face video’. Int. Symp. on Signal Processing and its Applications, 2007.
    26. 26)
      • 22. Masek, L.: ‘Recognition of human iris patterns for biometric identification’, 2003.
    27. 27)
      • 17. Huang, J., Ma, L., Tan, T., et al: ‘Learning based resolution enhancement of iris images’. British Machine Vision Conf., 2003.
    28. 28)
      • 15. Zhang, K., Tao, D., Gao, X., et al: ‘Learning multiple linear mappings for efficient single image super-resolution’, IEEE Trans. Image Process., 2015, 24, pp. 846–861.
    29. 29)
      • 21. Daugman, J.: ‘High confidence visual recognition of persons by a test of statistical independence’, IEEE Trans. Pattern Anal. Mach. Intell., 1993, 15, pp. 1148–1161.
    30. 30)
      • 1. Nguyen, K., Fookes, C., Sridharan, S., et al: ‘Robust mean super- resolution for less cooperative NIR iris recognition at distance and on the move’. Symp. on Information and Communication Technology, 2010.
    31. 31)
      • 13. Zhang, K., Gao, X., Tao, D., et al: ‘Single image super-resolution with multi-scale similarity learning’, IEEE Trans. Neural Netw. Learn. Syst., 2013, 24, pp. 1648–59.
    32. 32)
      • 9. Zhang, K., Gao, X., Tao, D., et al: ‘Single image super-resolution with non-local means and steering kernel regression’, IEEE Trans. Image Process., 2012, 21, pp. 4544–455.
    33. 33)
      • 32. Mezei, J., Morente-Molinera, J.A., Carlsson, C., et al: ‘Feature selection with fuzzy entropy to find similar cases’, Adv. Trends Soft Comput., 2014, 312, pp. 383–390.
    34. 34)
      • 26. Georgis, , Lentaris, G., Reisis, D., et al: ‘Single-image super-resolution using low complexity adaptive iterative back-projection’. IEEE Conf. on Digital Signal Proc., 2013.
    35. 35)
      • 41. Sheikh, , Bovik, A.C., de Veciana, G., et al: ‘An information fidelity criterion for image quality assessment using natural scene statistics’, IEEE Trans. Image Process., 2005, 14, pp. 2117–2128.
    36. 36)
      • 33. Carlsson, C., Heikkilä, M., Mezei, J., et al: ‘Fuzzy entropy used for predictive analytics’. IEEE Conf. on Fuzzy Systems, 2015.
    37. 37)
      • 6. Sun, J., Sun, J., Xu, Z., et al: ‘Image super-resolution using gradient profile prior’. IEEE Conf. on Computer Vision and Pattern Recognition, 2008.
    38. 38)
      • 31. Hu, M.: ‘Visual pattern recognition by moment invariants’, IRE Trans. Inf. Theory, 1962, 8, pp. 179–187.
    39. 39)
      • 42. Lukes, , Fliegel, K., Klíma, M., et al: ‘Performance evaluation of image quality metrics with respect to their use for super-resolution enhancement’, IEEE Fifth Int. Workshop on Quality of Multimedia Experience (QoMEX), 2013.
    40. 40)
      • 36. Abiyev, R.H.: ‘Neural network based biometric personal identification with fast iris segmentation’, J. Control Autom. Syst., 2009, 7, pp. 17–23.
    41. 41)
      • 25. He, H., Siu, W.-C.: ‘Single image super-resolution using Gaussian process regression’. IEEE Conf. Proc. on Pattern Recognition, 2011.
    42. 42)
      • 7. Xu, H., Zhai, G., Yang, X., et al: ‘Single image super-resolution with detail enhancement based on local fractal analysis of gradient’, IEEE Trans. Circuits Syst., 2013, 23, pp. 1740–1754.
    43. 43)
      • 35. Nozaki, K., Ishibuchi, H., Tanaka, H., et al: ‘Adaptive fuzzy rule-based classification systems’, IEEE Trans. Fuzzy Syst., 1996, 4, pp. 238–250.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2016.0075
Loading

Related content

content/journals/10.1049/iet-bmt.2016.0075
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading