Identify human personality parameters based on handwriting using neural network

The survey of person's handwriting and its parameters anatomy will lead the psychologists to investigate the psychological principles of behavior, temperament, character, personality and the nervous and social aspects of a person's brain. The human's handwritings in different psychological states including: anger, calm, happiness, excitement and different emotional states will show one's reaction or behavior at the same situations or same states. Analyzing one's handwriting is one of the scientific methods for evaluating and understanding one's personality. When a person's personality is analyzed, the effect of his personality or character on his/her handwriting is obvious and remarkable. The purpose of this method is to identify a person's personality through his/her handwriting. The literature shows that the identification and verification of human's identity from handwriting is common and relatively useful. Moreover, identification of one's identity from signature is more common. In this paper, in order to identify the character parameters in training stage, The Minnesota Multiphasic Personality Inventory was applied, and for identification of one's personality from his/her handwriting, a hidden Markov model and neural network (MLP) to perform classification was used so that MLP was used to identify those properties which are not related to the writer and a hidden Markov model was used to classify those properties which are related to the target writer. In this stage, in order to select the most similar image to the image of the input context, the image of input context after eliciting its property will be compared with all existing patterns in database. Finally the test output regarding the personality of the image of the target text which is recommended by the system will be introduced as the parameters of the output character.