LVQ-Neural Network Based Signature Recognition System Using Wavelet Features

  • S. A. Angadi
  • Smita Gour
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 222)


Signature recognition is an important requirement of automatic document verification system. Many approaches for signature recognition are presented in literature. A novel approach for off-line signature recognition system is presented in this paper, which is based on powerful wavelet features (maximum horizontal and vertical projection positions). The proposed system functions in three stages. Pre-processing stage; which consists of three steps: gray scale conversion, binarisation and fitting boundary box in order to make signatures ready for feature extraction, Feature extraction stage; where totally 64 wavelet based projection position features are extracted which are used to distinguish the different signatures. Finally in Neural Network stage; an efficient Learning Vector Quantization Neural Network (LVQ-NN) is designed and trained with 64 extracted features. The trained Neural Network is further used for signature recognition after the process of feature extraction. The average recognition accuracy obtained using this model ranges from 94 to 74 % with the training set of 15–50 persons.


LVQ-neural network Wavelet features Signature verification 


  1. 1.
    Porwik Piotr, Będzińska (2007) The compact three stages method of the signature recognition. 6th Int Conf Computer Inf Syst Ind Manage Appl (CISIM’07) 0–7695–2894–5, 07 IEEEGoogle Scholar
  2. 2.
    Saeed K, Adamski M (2005) Extraction of global features for offline signature recognitionGoogle Scholar
  3. 3.
    Kekre1 HB, Bharadi VA et al (2008) signature recognition by pixel variance analysis using multiple morphological dilationsGoogle Scholar
  4. 4.
    Jayasekara B, Jayasiri A, Udawatta L (2006) An evolving signature recognition system. First Int Conf Ind Inf Syst ICIIS 8–11Google Scholar
  5. 5.
    Kulkarni VB (207) A colour code algorithm for signature recognition. Electron Lett Comput Vision Image Anal 6(1):1–12Google Scholar
  6. 6.
    Desira M (2008) Handwritten signature verification by independent component analysisGoogle Scholar
  7. 7.
    Igarza JJ, Hernáez I, Goirizelaia I, Espinosa K, Escolar J (2005) Off-line signature recognition based on dynamic methods. Proc SPIE 5779:336–343Google Scholar
  8. 8.
    Özgündüz E, Şentürk T, Karslıgil ME (2005) Off-line signature verification and recognition by support vector machineGoogle Scholar
  9. 9.
    Beheshti SGS (2009) Off-Line Persian Signature Identification and Verification Based on Image Registration and Fusion. J Multimedia 4(3):137–144Google Scholar
  10. 10.
    Chalechale A, Naghdy G, Premaratne P, Mertins A (2004) Cursive signature extraction and verificationGoogle Scholar
  11. 11.
    Busch A, Boles WW (2002) Texture classification using multiple wavelet analysis. DICTA2002: Digital Image Comput Tech Appl 21–22 Google Scholar
  12. 12.
    Rahul Rithe (2006) Fuzzy logic based off-line signature verification and forgery detection system 1–8Google Scholar
  13. 13.
    Sabourin R, Drouhard JP (1992) Offline signature verification using directional PDF and neural networksGoogle Scholar
  14. 14.
    Mohammed A, Abdala, Yousif NA (2009) Offline signature recognition and verification based on artifical neural network. Eng Tech J 27:7Google Scholar
  15. 15.
    Hasna JFA (2006) signature recognition using conjugate gradient neural networks. World academy of science engineering and technology 20Google Scholar
  16. 16.
    Pérez-Hernández A, Sánchez A (2004) Vélez JF Simplified stroke-based approach for off-line signature recognitionGoogle Scholar
  17. 17.
    Endre Katona E (2012) Signature verification using neural netsGoogle Scholar
  18. 18.
    Jena D, Majhi B, Jena SK (2008) Improved offline signature verification scheme using feature point extraction method. J Comput Sci 4:2Google Scholar

Copyright information

© Springer India 2013

Authors and Affiliations

  • S. A. Angadi
    • 1
  • Smita Gour
    • 1
  1. 1.Department of Computer Science and EngineeringBasaveshwar Engineering CollegeBagalkotIndia

Personalised recommendations