Offline Text-Independent Writer Identification Based on Writer-Independent Model Using Conditional AutoEncoder

In a criminal investigation, a writer identification is frequently performed to find out what kind of writer a certain letter was written. In comparing the similarity between the handwriting of both documents, it is necessary to extract a person's characteristic writing style. Although the text-dependent methods have been studied show high discrimination performance for a writer identification, the situation assumed in the actual appraisal that the same character class does not exist is not supported. In this research, we propose a writer identification method taking into account the actual appraisal situation. We define the handwriting features without dependence on character class as "personal writing style" and construct the AutoEncoder with the condition of character class to extract personal writing style from a single character sample. In the latent space trained by the conditional AutoEncoder, similar personal writing styles are mapped on to neighboring points independent of the character class. At the time of writer identification, the similarity between the handwriting feature of unknown writer and reference writer in the latent space is evaluated. In order to confirm the effectiveness of the proposed method, we conducted a writer identification experiments using ETL-1 Character Database and NIST Special Database 19 2nd Edition. As a result, it is indicated that it is possible to extract personal writing style, which is an effective feature for writer identification, even under conditions close to the practical situation.