Image Compression using Discrete Cosine Transform (DCT) and Features Level Fusion in the Recognition for Multimodal Authentication Biometrics System

  • Authors

    • Fatma Susilawati Mohamad
    • Khaled Alhadi Meftah
    https://doi.org/10.14419/ijet.v7i3.28.23414
  • Multimodal Biometrics, Fusion, CCA, DCT, Features Level Fusion.
  • Multimodal biometrics have an important role in security systems by detecting security breaches and authentication systems, as well as security and confidentiality of information transmission. Sometimes, some factors affect the system's authentication noise and lightness when using a single biometric. So, in this paper, we will present a proposal for an authentication system through the compression dataset images using Discrete Cosine Transform (DCT). After extracting the features of each biometric separately (such as face - fingerprint - fingervein - iris), features extraction were normalized and all two biometrics were fusion (such as Face & Fingerprint – Face & Fingervein - Face & Iris – Fingerprint & Fingervein – Fingerprint & Iris – Fingervein & Iris) by the application of a method- Canonical Correlation Analysis (CCA). Recognition results were recorded. We obtained the best recognition rate between each merger by combining biometrics and we find the best rate of accuracy 98.1132%.

     

  • References

    1. [1] Malathi, R. (2016). An integrated approach of physical biometric authentication system. Procedia Computer Science, 85, 820-826.

      [2] Mishra, A. (2010). Multimodal biometrics it is: Need for future systems. International Journal of Computer Applications, 3(4), 28-33.

      [3] Assaad, F. S., & Serpen, G. (2015). Transformation based score fusion algorithm for multi-modal biometric user authentication through ensemble classification. Procedia Computer Science, 61, 410-415.

      [4] Shyam, R., & Singh, Y. N. (2015). Identifying individuals using multimodal face recognition techniques. Procedia Computer Science, 48, 666-672.

      [5] Prabhu, G., & Poornima, S. (2015). Minimize search time through gender classification from multimodal biometrics. Procedia Computer Science, 50, 289-294.

      [6] Wild, P., Radu, P., Chen, L., & Ferryman, J. (2016). Robust multimodal face and fingerprint fusion in the presence of spoofing attacks. Pattern Recognition, 50, 17-25.

      [7] Khandelwal, C. S., Maheshewari, R., & Shinde, U. B. (2016). Review paper on applications of principal component analysis in multimodal biometrics system. Procedia Computer Science, 92, 481-486.

      [8] Raid, A. M., Khedr, W. M., El-Dosuky, M. A., & Ahmed, W. (2014). Jpeg image compression using discrete cosine transform-A survey. International Journal of Computer Science and Engineering Survey, 5(2), 39-47.

      [9] Delac, K., Grgic, M., & Grgic, S. (2005). Independent comparative study of PCA, ICA, and LDA on the FERET data set. International Journal of Imaging Systems and Technology, 15(5), 252-260.

      [10] Kulkarni, S., Raut, R. D., & Dakhole, P. K. (2016). A novel authentication system based on hidden biometric trait. Procedia Computer Science, 85, 255-262.

      [11] Mansur, M. A., Khalifa, N., Abdelhafid, A. I. M., Mohamed, A. H., Hend, H. A. A., Javad, R., & Aybaba, H. (2017). Finger vein recognition with gray level co-occurrence matrix based on discrete wavelet transform. International Journal of Computer Science Technology, 8(2), 108-112.

      [12] Kumar, N., & Verma, P. (2012). Fingerprint image enhancement and minutia matching. International Journal of Engineering Sciences & Emerging Technologies, 2(2), 37-42.

      [13] Malathi, R. (2016). An integrated approach of physical biometric authentication system. Procedia Computer Science, 85, 820-826.

      [14] MathWorks. (2018). Norm. https://www.mathworks.com/help/matlab/ref/norm.html#bt0y64c-1.

      [15] Krzanowski, W. (2000). Principles of multivariate analysis. OUP Oxford.

      [16] Haghighat, M., Abdel-Mottaleb, M., & Alhalabi, W. (2016). Discriminant correlation analysis: Real-time feature level fusion for multimodal biometric recognition. IEEE Transactions on Information Forensics and Security, 11(9), 1984-1996.

      [17] Sun, Q. S., Zeng, S. G., Liu, Y., Heng, P. A., & Xia, D. S. (2005). A new method of feature fusion and its application in image recognition. Pattern Recognition, 38(12), 2437-2448.

  • Downloads

  • How to Cite

    Susilawati Mohamad, F., & Alhadi Meftah, K. (2018). Image Compression using Discrete Cosine Transform (DCT) and Features Level Fusion in the Recognition for Multimodal Authentication Biometrics System. International Journal of Engineering & Technology, 7(3.28), 173-176. https://doi.org/10.14419/ijet.v7i3.28.23414