Personality Trait Identification Using Unconstrained Cursive and Mood Invariant Handwritten Text

Abstract

Identification of Personality is a complex process. Personality traits are stable over time .Individual"s behavior naturally varies from occasion to occasion. But there is a core consistency which defines the true nature. The paper addresses this issue of behavior. Graphology is normally a technique used to identify the traits. Accuracy of this technique depends on how skilled the analyst is. Although human intervention in handwriting analysis has been effective, but it is costly and prone to fatigue. An automation of handwritten text is proposed. Basically we have considered three important features in the direction of orientation of the lines :(i) up hill (ii) down hill (iii) constant line. Edge histogram and bounding boxes was used for feature extraction .Known classifiers like SVM & ANN are used for training and the results were compared. The results were about 98% for SVM & 70% with ANN. The analysis was done using single line.

Automated handwriting analysis based on pattern recognition: a survey

“…Many researchers have worked to make the dataset. Several factors must be considered as follows: defining a group of the respondent that might be included the ratio of male-female [19], group of age [6,7,19], specification of paper size [15,20], type of pen (ballpoint or ink pen) and ink colors [20]. After the data is taken, then the data acquisition process is carried out in digital form using a scanner.…”

“…A different approach by [33], it has been Farsi's handwriting to analyze human behavior through handwriting with SVM classifier has been considered different features as an input to analyze personality traits from handwriting and the system showed promising results. Another research has been proved that the SVM classifier can perform better to reach maximum accuracy and SVM showed superior accuracy with 98% and ANN with 70% [20]. Two years later, the author's had been studying to analyze handwriting using cursive O letter (FCC and zoning features) with trained by SVM classifier and gave accuracy with 86.66% [19].…”

“…SVM is only able to handle the classification of two classes, but there has been a lot of research in handwriting pattern recognition using multiclass SVM [7,40,41]. SVM has proven the highest achievement accuracy of classification [7,20,41]. It must be underlined that the accuracy achieved by SVM is only in the classification of one feature [20].…”

“…SVM has proven the highest achievement accuracy of classification [7,20,41]. It must be underlined that the accuracy achieved by SVM is only in the classification of one feature [20]. In several cases, determining the classification of personality traits using complex features, the results obtained are not too significant [19,29,33,35].…”