Writer Identification System for Indic and Non-Indic Scripts: State-of-the-Art Survey

Writer identification is a challenging move in the field of pattern recognition and reflects advanced perceptions into the handwriting research. It is the process of determining the author or writer of the text by matching it with the training database. It is an exigent task because the writing style of an individual is distinct from other because of unique intrinsic characteristics and is different even if the same writer writes that text with the same pen next time. It is concerned with the writing styles, feelings, perception, behavior and the brain of an individual and it is one of the neoteric applications of biometric identification. Biometric identification is the branch of computer science that deals with identification of an individual from a group using unique identifiers such as fingerprints, retina, handwriting and signatures. It is a term used for the body measurements and calculations. This paper presents a comprehensive and transparent panorama on the work done for the writer identification system on different Indic and non-Indic scripts and a widespread view towards this peculiar research area. The structure of the paper comprises introduction, motivation for the work, background, sources of information, schemes, process, reported works, synthesis analysis, study of features and classifiers for writer identification, and finally the conclusion and future directions. The main focus of this paper is to present in a systematic way, the reported works on writer identification systems on Indic scripts such as Bengali, Gujarati, Gurumukhi, Kannada, Malayalam, Oriya, Tamil and Telugu and Non-Indic scripts such as Arabic, Chinese, French, Persian, Roman and finally exposes the synthesis analysis based on the findings. This study gives the cognizance and beneficial assistance to the novice researchers in this field by providing in a nut shell the studies of various feature extraction methods and classification techniques required for writer identification on both Indic and non-Indic scripts. It is observed that work done on the writer identification systems with good accuracy rates in Indic scripts is limited as compared to non-Indic scripts and truly presents a future direction.