Image anonymization using clustering with pixelization

  • Authors

    • Ria. Elin Thomas
    • Sharmila K. Banu
    • B K. Tripathy
    2018-06-08
    https://doi.org/10.14419/ijet.v7i2.33.15548
  • Fuzzy C-Means Clustering, Image Anonymization, Pixelization, Privacy.

  • With the increasing usage of images to express opinions, feelings and one’s self, on social media, and other websites, privacy concerns become an issue. The need to anonymize a person’s face, or other aspects presented in an image for legal or personal reasons has sometimes been overlooked. Pixelization is a common technique that is used for anonymizing images. However, this technique has been proved to be a not-so-reliable technique, as the images can be restored using de-pixelization techniques. Clustering is usually used in relation to images, for image segmentation. When used in combination with pixelization, it proves to be an effective way to anonymize images. In this paper, the authors investigate the cons of using only pixelization, and prove how the use of clustering can improve the chances of anonymizing effec-tively.

     

     


     

  • References

    1. [1] Dufaux, F., & Ebrahimi, T. (2010, July). A framework for the validation of privacy protection solutions in video surveillance. In Multimedia and Expo (ICME), 2010 IEEE International Conference on (pp. 66-71). IEEE.

      [2] Honda, K., Omori, M., Ubukata, S., & Notsu, A. (2015, June). A privacy-preserving crowd movement analysis by k-member clustering of face images. In Informatics, Electronics & Vision (ICIEV), 2015 International Conference on (pp. 1-5). IEEE.

      [3] Honda, K., Omori, M., Ubukata, S., & Notsu, A. (2015, November). A study on fuzzy clustering-based k-anonymization for privacy preserving crowd movement analysis with face recognition. In Soft Computing and Pattern Recognition (SoCPaR), 2015 7th International Conference of (pp. 37-41). IEEE.

      [4] Birnstill, P., Ren, D., & Beyerer, J. (2015, August). A user study on anonymization techniques for smart video surveillance. In Advanced Video and Signal Based Surveillance (AVSS), 2015 12th IEEE International Conference on (pp. 1-6). IEEE.

      [5] Shahbaz, S., Mahmood, A., & Anwar, Z. (2013, December). SOAD: Securing oncology EMR by anonymizing DICOM images. In Frontiers of Information Technology (FIT), 2013 11th International Conference on (pp. 125-130). IEEE.

      [6] Indhumathi, R., & Priya, S. M. (2014). Data Preserving By Anonymization Techniques for Collaborative Data Publishing. International Journal of Innovative Research in Science, Engineering and Technology, 3(1), 358–363.

      [7] Monteiro, E., Costa, C., & Oliveira, J. L. (2015, August). A machine learning methodology for medical imaging anonymization. In Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE (pp. 1381-1384). IEEE.

      [8] Ruchaud, N., & Dugelay, J. L. (2016). Automatic Face Anonymization in Visual Data: Are we really well protected?. Electronic Imaging, 2016(15), 1-7.

      [9] Pantoja, C., Arguedas, V. F., & Izquierdo, E. Anonymization and De-identification of Personal Surveillance Visual Information: A Review.

      [10] Cavedon, L., Foschini, L., & Vigna, G. (2011, August). Getting the Face behind the Squares: Reconstructing Pixelized Video Streams. In WOOT (pp. 37-45).

      [11] Keys, R. (1981). Cubic convolution interpolation for digital image processing. IEEE transactions on acoustics, speech, and signal processing, 29(6), 1153-1160.

      [12] Dong, W., Zhang, L., Shi, G., & Wu, X. (2011). Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization. IEEE Transactions on Image Processing, 20(7), 1838-1857.

      [13] Dunn, J. C. (1973). A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters.

      [14] Bezdek, J. C., Ehrlich, R., & Full, W. (1984). FCM: The fuzzy c-means clustering algorithm. Computers & Geosciences, 10(2-3), 191-203.

      [15] B.K.Tripathy and P.Swarnalatha: A Comparative Study of RIFCM with Other Related Algorithms from Their Suitability in Analysis of Satellite Images using Other Supporting Techniques, Kybernetes, vol.43, no.1,(2014), pp. 53-81

      [16] B.K.Tripathy, R. Bhargav, A. Tripathy, E. Verma, Raj Kumar and P.Swarnalatha: Rough Intuitionistic Fuzzy C-Means Algorithm and a Comparative Analysis, COMPUTE‟13, Aug 22-24, Vellore, Tamil Nadu, India Copyright 2013 ACM 978-1-4503-2545-5/13/08

      [17] B.K.Tripathy and R. Bhargav: Kernel Based Rough-Fuzzy C-Means, PReMI, ISI Calcutta, December, LNCS 8251, (2013), pp.148-157

      [18] Swarnalatha P, Tripathy B.K., Nithin, P. L. and D. Ghosh: Cluster Analysis Using Hybrid Soft Computing Techniques, CNC-2014International Conference of Network and Power Engineering ,Proceedings of Fifth CNC-2014,pp. 516-524

      [19] B.K.Tripathy, Avik Basu and Sahil Govel: Image segmentation using spatial intuitionistic fuzzy C-means clustering, proceedings of the IEEE ICCIC2014, (2014), pp.878-882

      [20] B.K.Tripathy and D. Mittal: Efficiency Analysis of Kernel Functions in Uncertainty Based C-Means Algorithms, International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015, Article number 7275709, pp. 807-813 (2015).

      [21] B.K. Tripathy, Deepthi P.H. and Dishant Mittal: Hadoop with Intuitionistic Fuzzy C-means for clustering in Big Data, Advances in Intelligent Systems and Computing, Volume 438, 2016, Pages 599-610.

      [22] B. K. Tripathy, Akarsh Goyal and Rahul Chowdhury: MMeNR: Neighborhood Rough Set Theory Based Algorithm for Clustering Heterogeneous Data, International Conference on Inventive Communication and Computational Technologies (ICICCT 2017), (2017), pp.323-328.

  • Downloads

  • How to Cite

    Elin Thomas, R., K. Banu, S., & K. Tripathy, B. (2018). Image anonymization using clustering with pixelization. International Journal of Engineering & Technology, 7(2.33), 990-993. https://doi.org/10.14419/ijet.v7i2.33.15548