Writer identification is the task of finding the writer of a specific document. It helps forensic experts in taking their decisions regarding the authenticity of a questioned document. Writer identification is not an easy problem, because a writer never reproduces the same text exactly alike. However, the difference in the writing style within one writer is generally less meaningful comparing to the difference between two different writers. Writer identification is also a very active research field.
Writer identification generally requires two main steps. The first one is an image-processing step in which, features are extracted from the questioned document and all the documents of the database. The second step is a classification step, in which the questioned document is assigned to the “closest” document in the dataset according to the difference between their features.