Detecting features of human personality based onhandwriting using learning algorithms

Handwriting analysis is useful for understanding thepersonality characteristics through the patterns created bythe handwriting and can reveal features such as mental andemotional instability. On the other hand, it is difficult todetermine the personality, especially when it is associatedwith the law because there is no threshold or scale beingable to make detailed results of the analysis. This thesis aimsto provide an automated solution to recognize thepersonality of the author by combining image processingand pattern recognition techniques. The personalityrecognition system proposed in this project is composed oftwo main parts: training and testing. In the training part,after feature extraction from all image patterns of the inputtext, a proportional output is created through the MMPIpersonality test. Then these inputs are trained to the neuralnetwork as a pattern. As a result of this training, acomprehensive database will be formed. In the testing part,the database is used as a main comparison reference. Afterfeature extraction, the input text image is compared with allpatterns in the database to find the closest image to the inputtext image. Finally, the MMPI personality test output for theproposed text image is introduced as the output personalityparameters.