Personality Traits Identification Through Handwriting Analysis

Mekhaznia, Tahar; Djeddi, Chawki; Sarkar, Sobhan

doi:10.1007/978-3-030-71804-6_12

Cited by 13 publications

(6 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In comparison to Mekhaznia et al [7] proposed solution had 8% higher accuracy. In comparison to Chaubey and Arjaria [29] proposed solution has 43% higher accuracy.…”

Section: Resultsmentioning

confidence: 71%

“…The classification error rate is compared across the solutions and the result is given in Figure 5. The error rate is lower in proposed solution at 0.1 compared to 0.16 in Rahman and Halim [30], 0.21 in Mekhaznia et al [7] and 0.54 in Chaubey and Arjaria [29]. The error rate has lowered due to selection of most relevant features for classification in the proposed solution.…”

Section: Figure 4 Roc Plotmentioning

confidence: 80%

“…(2021) [7], Chaubey and Arjaria (2022) [29] were used. The accuracy results for different personality types are given in Table 7.…”

Section: Resultsmentioning

confidence: 99%

“…Chaubey and Arjaria [29] used entire image for personality classification without selection of significant features, due to which accuracy is low. Mekhaznia et al [7] extracted only edge based features due to which the accuracy is low. The receiver operating characteristic curve (ROC) plot comparing the solutions is given in Figure 4.…”

Section: Resultsmentioning

confidence: 99%

“…The personality model used in this work is outdated compared to big five personality assessment. Mekhaznia et al [7] extracted textural features from handwritten image documents. Neural network classified the textural features to two different personalities of the individual.…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

A self adaptive cognitive deep learning framework for classifying graphology features to Big five personality traits

2022

IJATEE

View full text Add to dashboard Cite

Graphology is a technique for study and analysis of individual personality from his/her handwriting style. Most of the existing graphology-based solutions for personality detection recognize nonstandard application dependent personalities. Even the very few big five personality recognition approaches have limited accuracy and lacks adaptivity to new handwriting styles. Towards these problems, a novel self-adaptive cognitive learning framework based on deep learning convolutional neural network (CNN) features is proposed to classify the handwritten document to big five personality traits. This framework correlates the various document level and character level graphology features to big five personality traits to recognize features with strong correlation to various big five personality traits and uses these features to classify the personality. To enhance the deep learning feature learning ability an enhanced convolution kernel is proposed for the CNN. Through testing with various handwritten documents, the proposed solution is found to provide 2.18% higher accuracy and 5% lower false positives compared to existing works on big five personality classification.

show abstract

“…In comparison to Mekhaznia et al [7] proposed solution had 8% higher accuracy. In comparison to Chaubey and Arjaria [29] proposed solution has 43% higher accuracy.…”

Section: Resultsmentioning

confidence: 71%