Off-Line Arabic Signature Recognition Based on Invariant Moments Properties


In this paper, a number of persons were selected to use their signature as adatabase for the work. Six signatures were taken from each person through twoseparated period of time using the same pen and paper. The adopted method consists ofthree main steps. In the first step, the digital image of the signature transformed intocontours. After that the main contours were extracted and the noise was rejected. Theseextracted contours and their dimensions were measured precisely according to their (x)and (y) axis. Second step is the coding step, where the (Chain Code) method was usedto code the extracted contour from the first step, converted them into vectors in whichthey are very easy to deal with. Using length of the vectors were sorted descending bythat can be easily used in comparison process. The third (final) step includesapplication of the (Invariant Moments) method with these chain vectors and thecalculated mean of the output for the five signatures taken for each signer and used itas a reference feature for the signer in the recognition process. The signaturerecognition process completed using the (Minimum Distance) method as a classifier toidentify the personal signature.