Authors :
Dr. Deepu R; Suman K.M; S. S. Surabhi; Nischal S; Nisarga P.
Volume/Issue :
Volume 7 - 2022, Issue 7 - July
Google Scholar :
https://bit.ly/3IIfn9N
Scribd :
https://bit.ly/3b8z1kp
DOI :
https://doi.org/10.5281/zenodo.6910789
Abstract :
Graphology is a method of identifying,
evaluating and understanding human personality traits in
person by analysing the strokes and patterns revealed by
their handwriting. Handwriting shows a person’s genuine
nature, including emotional outlay, fears, honesty,
defences and many other traits. Graphologists, who
analyse handwriting professionally, usually determine the
writer from a piece of handwriting. The analyst's level of
expertise affects how accurate the analysis is. Despite
being effective, human assistance in handwriting analysis
is expensive and error-prone. Hence, the proposed
methodology focuses on developing a system that employs
machine learning to predict personality traits without the
need for human interaction. To make this happen, we
look at handwriting features in a document to predict a
writer's personality traits.After extracting all required
features from the image containing the handwriting,
DenseNet are trained which output personality trait of
the writer. The emotions are depression, anxiety, panic,
stress and no sign of psychological issues are been
predicted. For the project, 4899 images of handwriting
samples have been acquired.
Keywords :
Graphology, Human Personality, Psychological Analysis, Image Processing, Machine Learning, Densely Connected Convolutional Network.
Graphology is a method of identifying,
evaluating and understanding human personality traits in
person by analysing the strokes and patterns revealed by
their handwriting. Handwriting shows a person’s genuine
nature, including emotional outlay, fears, honesty,
defences and many other traits. Graphologists, who
analyse handwriting professionally, usually determine the
writer from a piece of handwriting. The analyst's level of
expertise affects how accurate the analysis is. Despite
being effective, human assistance in handwriting analysis
is expensive and error-prone. Hence, the proposed
methodology focuses on developing a system that employs
machine learning to predict personality traits without the
need for human interaction. To make this happen, we
look at handwriting features in a document to predict a
writer's personality traits.After extracting all required
features from the image containing the handwriting,
DenseNet are trained which output personality trait of
the writer. The emotions are depression, anxiety, panic,
stress and no sign of psychological issues are been
predicted. For the project, 4899 images of handwriting
samples have been acquired.
Keywords :
Graphology, Human Personality, Psychological Analysis, Image Processing, Machine Learning, Densely Connected Convolutional Network.