Personality Recognition Based on Handwriting Types Using Fuzzy Inference

Graphology is the psycho-analysis study of personality and individual characteristics of writers based on the handwriting types. Graphology is a time-consuming and complicated task. Due to small number of expert graphologists, computerized measurement of graphology is an essential need. In this research, in addition to extraction of handwriting features, it is tried to categorize them in terms of regularity and inequality of letters and recognize person’s characteristics via graphology tables. This classification includes these types of handwriting: spontaneous, with difference in pen pressure, uncoordinated, coordinated with partial variance, uniform, sharp, regular, with inequality of letter’s inflexion and unequal. In this paper, 140 typical Farsi handwriting samples are used which are interpreted after giving MMPI (Minnesota Multiphasic Personality Inventory) questionnaire. The novel proposed features are used as the Mamdani fuzzy classifier inputs. Variance of baseline curves, variance of distances between words, variance of vertical letter height, variance of pen width, number of zero, acute and obtuse angles and their ratios to the number of text lines and slope angle are used as features for Mamdani fuzzy classifier inputs. In this study, there are nine handwriting types for personality recognition and 24 rules are defined for the nine fuzzy systems. Compared to our ground truth (MMPI results for the handwriting database), the proposed method showed an accuracy of 82.5% for personality recognition that demonstrated promising results.