Online Writer Identification Using Fuzzy C-means Clustering of Character Prototypes

New kinds of documents such as handwritten online documents are emerging, which are produced by digital devices such as Tablet PC, personal handheld devices or digital paper coupled with digital pens. The rapid increase in the number of such handwritten online documents leads to mounting pressure on finding innovative solutions towards faster processing, indexing and retrieval of the documents from databases. One such method is to extract writer information derived from the raw ink signal for indexing and retrieval of the documents. This paper proposes a text independent method that does not place any constraints on the content being written or writing styles of the writers. We subsequently extract writer information at the character level from online handwritten documents and present a fuzzy c-means approach to cluster and classify the character prototypes for writer identification. The proposed system attained an accuracy of 97.6% on 82 writers and an accuracy of 98.3% when retrieved from a scaled up larger database of 120 writers.