Detection and Feature Extraction for Images Signatures

  • Authors

    • Fatma Susilawati Mohamad
    • Fadi Mohammad Alsuhimat
    • Mohamad Afendee Mohamed
    • Mumtazimah Mohamad
    • Azrul Amri Jamal
    2018-08-17
    https://doi.org/10.14419/ijet.v7i3.28.20963
  • Feature Extraction, Feature Detection, HARRIS, FAST, BRISK.

  • The signing process is one of the most important processes used by organizations to ensure the confidentiality of information and to protect it against any unauthorized penetration or access to such information. As organizations and individuals enter the digital world, there is an urgent need for a digital system capable of distinguishing between the original and fraud signature, in order to ensure individuals authorization and determine the powers allowed to them. In this paper, three widely used feature detection algorithms, HARRIS, BRISK (Binary Robust Invariant Scalable Keypoints) and FAST (Features from Accelerated Segment), these algorithms are compared to calculate the run time and accuracy for set of signature images. Three techniques have been applied using (UTSig) dataset; the experiment consisted of four phases: first, applying the techniques on one image, then on four images, then on eight images, finally applying the techniques on ten images where time and accuracy were calculated for each algorithm in the all phases. The results showed that the BRISK algorithm got the best result among the feature detection algorithm in terms of accuracy and the FAST algorithm got the best result among the feature detection algorithm in terms of run time.

                                                                                                                                                                                                       

     

  • References

    1. [1] Fotak T, Baca M, Koruga P. Handwritten signature identification using basic concepts of graph theory. WSEAS Transactions on Signal Processing. 2011, 4(7): 117-129.

      [2] Daqrouq K, Sweidan H, Balamesh A, Ajour M. Off-Line Handwritten Signature Recognition by Wavelet Entropy and Neural Network. Entropy. 2017, 19(6): 1-20.

      [3] Jahan T, Anwar S, Al-Mamun A. A Study on Preprocessing and Feature Extraction in offline Handwritten Signatures. Global Journal of Computer Science and Technology: F Graphics and Vision. 2015, 15(2): 1-7.

      [4] Gunjal S, Dange B, Brahmane A. Offline Signature Verification using Feature Point Extraction. International Journal of Computer Applications. 2016, 141(14): 6-12.

      [5] Hafemann L, Sabourin R, Oliveira L. Learning features for offline handwritten signature verification using deep convolutional neural networks. Pattern Recognition. 2017, 70(1): 163-176.

      [6] Ghosh P, Pandey A, Pati U. Comparison of Different Feature Detection Techniques for Image Mosaicing. ACCENTS Transactions on Image Processing and Computer Vision. 2015, 1(1): 1-7.

      [7] Trajkovic M, Hedley M. FAST corner detector. Image and Vision Computing. 1998, 16(2): 75-87.

      [8] Leutenegger S, Chli M, Siegwart R. BRISK: Binary Robust Invariant Scalable Key points. Proceedings of the IEEE International Conference on Computer Vision, 2011.

      [9] Uliyan D, Jalab H, Abdul Wahab, A, Sadeghi S. Image Region Duplication Forgery Detection Based on Angular Radial Partitioning and Harris Key-Points. Symmetry. 2016, 8(62): 1-19.

      [10] Patil P, Chavan M. A Comparative Analysis of Image Stitching Algorithms Using Harris Corner Detection and SIFT Algorithm. International Journal of Engineering Research and Technology. 2017, 10(1): 482-486.

      [11] Soleimani A, Fouladi k, Araabi B. UTSig: A Persian offline signature dataset. IET Biometrics. 2016, 6(1): 1-8.

  • Downloads

  • How to Cite

    Susilawati Mohamad, F., Mohammad Alsuhimat, F., Afendee Mohamed, M., Mohamad, M., & Amri Jamal, A. (2018). Detection and Feature Extraction for Images Signatures. International Journal of Engineering & Technology, 7(3.28), 44-48. https://doi.org/10.14419/ijet.v7i3.28.20963