TY - JOUR ID - TI - Off-Line Arabic Signature Recognition Based On Invariant Moments Properties AU - Rassoul Adhaem Hamied AU - Yasser Chasib Bucheet AU - Mohammad Ismail Abd-Almajied PY - 2011 VL - IS - 6 SP - 249 EP - 272 JO - Journal of College of Education مجلة كلية التربية SN - 18130380 AB - The signature recognition process is special case of handwrittenrecognition. The process includes many complexity, where the signature isa dynamic feature that affected by many operators like psychology, thekind of pen and paper and other operators. In this paper, a number ofpersons were selected to use their signature as a database for the work. Sixsignatures were taken from each person through two separated period oftime using the same pen and paper. The adopted method consists of threemain steps. In the first step, the digital image of the signature transformedinto contours. After that the main contours were extracted and the noisewas rejected. These extracted contours and their dimensions were measuredprecisely according to their (x) and (y) axis. Second step is the coding step,where the (Chain Code) method was used to code the extracted contourfrom the first step, converted them into vectors in which they are very easyto deal with. Using length of the vectors were sorted descending by that canbe easily used in comparison process. The third (final) step includesapplication of the (Invariant Moments) method with these chain vectorsand the calculated mean of the output for the five signatures taken for eachsigner and used it as a reference feature for the signer in the recognitionprocess. The signature recognition process completed using the (MinimumDistance) method as a classifier to identify the personal signature.

ER -