Evaluation and Categorization of Handwriting Patterns reflecting Sentiments
Mohammad Shabaz1, Urvashi Garg2
1Mohammad Shabaz, Department of Computer Science Engineering, Chandigarh University, Mohali, India.
2Urvashi Garg, Department of Computer Science Engineering, Chandigarh University, Mohali, India.
Manuscript received on 01 March 2019 | Revised Manuscript received on 09 March 2019 | Manuscript published on 30 July 2019 | PP: 2475-2477 | Volume-8 Issue-2, July 2019 | Retrieval Number: B2081078219/19©BEIESP | DOI: 10.35940/ijrte.B2081.078219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Uniqueness lies in every living being that exists on the earth. It can be viewed through its behavior, walking, personality, dressing, cramming, writing and many more. Handwriting is an important aspect that reflects the uniqueness as a whole, but when it is restricted to find sentiments it does shows certain patterns. This research is dedicated to evaluate the handwriting patterns reflecting sentiments. The major challenge faced during this research is the mood of an individual while collecting the handwriting samples. The process starts, when an observer recites a joke and the audience is given a plane piece of paper and asked them to write “I LIKE IT” those who laugh or smile and “I DON’T LIKE IT” those who do not. The collected samples are then segmented at the depth of Letter ‘L’ which is either viewed as a parabola or straight line till it touches the Letter ‘I’ with image dimensions (160, 65) pixels. It is found that the value of the standard deviation of pixels goes to 14 those who laugh at their extreme and those who just smile goes to 8. Thus, it is concluded that the level of joy of an individual from smile to laugh is in between the standard deviation of pixel value ranging from 8 to 14. It can also be concluded that the handwriting changes immediately after laughing or listening a joke. Thus handwriting goes on changing when someone becomes joyful. Testing these patterns further on another blinded sample, the technique provides a result with an accuracy percentage of 97.
Index Terms: Sentiments, Graphology, Handwriting Analysis, Pattern Evaluation.
Scope of the Article: Patterns and Frameworks