Personal identification by handwriting is a very important research topic in biometrics. A wide variety of applications require reliable verification schemes to confirm an identity of an individual. Text-independent writer identification has gained much attention for its advantage of high security. In this paper, based on the analysis of recent research on writer identification by text-independent handwriting as well as text-dependent handwriting, we proposed some algorithms for writer identification by text-Independent handwriting. The main contributions of this paper are as follows: [1] By analyzing the common dynamic features of handwriting, an identification method based on compound dynamic features is proposed. This method extracts the relations between every two dynamic features, and can provide more information for writers identifying than the method proposed before. [2] A writer identification method based ICA(Independent Component Analysis) is proposed. ICA is employed to process dynamic handwriting data, which can make full use of the spatial distribution of the dynamic features. [3] Text-independent writer identification based on fusion of dynamic and static features is proposed. By this method, we has improved the identification accuracy and reduced the required data number.
修改评论