Slant algorithm for online signature recognition

Designing the algorithm to extract features in signature is a challenging task due to complex human behavior which is developed through repetition. Features such as direction, slant, baseline, pressure, speed and numbers of pen ups and downs are some of the dynamic information signature that can be extracted from an online method. However, the variables for identifying the features is rarely discussed and notified. Therefore, this paper presents the variables that involve in designing the algorithm for extracting the slant features. Both local and global slant characteristics are considered in extracting the features. Local slant is the longest slant among the detected slant while the global slant represents the highest quantity of classified slant whether the slant are leftward, upright or rightward. Signature Extraction Features System (SEFS) is used to extract the slant features in signature automatically for analysis purposes. The images created by SEFS are used as samples for the questionnaire to identify the slant features and to be given to human expert for evaluation. The results from the SEFS are compared with the result from the questionnaire. The results demonstrate a competitive performance with 85% accuracy.

[1]  Réjean Plamondon,et al.  DESIGNING AN AUTOMATIC SIGNATURE VERIFIER: PROBLEM DEFINITION AND SYSTEM DESCRIPTION , 1990 .

[2]  S. V. Wunnava,et al.  An efficient scheme for dynamic signature verification , 1996, Proceedings of SOUTHEASTCON '96.

[3]  Yan Solihin,et al.  Slant manipulation and character segmentation for forensic document examination , 1996, Proceedings of Digital Processing Applications (TENCON '96).

[4]  Sung-Hyuk Cha,et al.  Approximate stroke sequence string matching algorithm for character recognition and analysis , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[5]  Michael Fairhurst,et al.  Strategies for exploiting signature verification based on complexity estimates , 2002 .

[6]  Alisher Kholmatov,et al.  Biometric identity verification using on-line & off-line signature verification , 2003 .

[7]  M. Miyatake,et al.  Dynamic features extraction for on-line signature verification , 2004, 14th International Conference on Electronics, Communications and Computers, 2004. CONIELECOMP 2004..

[8]  A. El Saddik,et al.  A stroke based algorithm for dynamic signature verification , 2004, Canadian Conference on Electrical and Computer Engineering 2004 (IEEE Cat. No.04CH37513).

[9]  Wataru Ohyama,et al.  Local slant estimation for handwritten English words , 2004, Ninth International Workshop on Frontiers in Handwriting Recognition.

[10]  S. Madabusi,et al.  On-line and off-line signature verification using relative slope algorithm , 2005, Proceedings of the 2005 IEEE International Workshop on Measurement Systems for Homeland Security, Contraband Detection and Personal Safety Workshop, 2005. (IMS 2005).

[11]  Seiichi Uchida,et al.  An HMM implementation for on-line handwriting recognition based on pen-coordinate feature and pen-direction feature , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[12]  Shuzlina Abdul Rahman,et al.  Online Slant Identification Algorithm Using Vector Rules , 2008, ICCSA.