Writer identification based on graphology techniques

摘要

Herein, an innovative system biometric of specific writers' identification based on technical expert calligraphic and graphology on handwritten script is presented. It has been developed working in the off-line mode on a Spanish words image database, formed by 29 different individuals. All extractions of characteristics carried out on the images have been used for the identification and were carried out by means of the estimate of several elements objects using studies from The French Graphology School. They are commonly employed by handwriting experts in judicial matters. The success percentage achieved with five of these characteristics from this database of 29 writers is 99.34%. In new experimentation, with these same parameters and enlarging the database to 70 users, a success rate of 92% was reached.