Handwriting Classification Based on Support Vector Machine with Cross Validation

Hasseim, Anith Adibah; Sudirman, Rubita; Khalid, Puspa Inayat

doi:10.4236/eng.2013.55b017

Cited by 16 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…gradient features to classify the writer's age, gender and handedness: the histogram of oriented gradients and gradient local binary patterns. They used the Support Vector Machine (SVM) [18], method to classify the documents. IAM and Khatt datasets were used to evaluate the system.…”

Section: Related Workmentioning

confidence: 99%

Transfer Learning to Detect Age From Handwriting

AL-Qawasmeh¹,

Suen²

2022

AAIML

View full text Add to dashboard Cite

Handwriting analysis is the science of determining an individual’s personality from his or her handwriting by assessing features such as slant, pen pressure, word spacing, and other factors. Handwriting analysis has a wide range of uses and applications, including dating and socialising, roommates and landlords, business and professional, employee hiring, and human resources. This study used the ResNet and GoogleNet CNN architectures as fixed feature extractors from handwriting samples. SVM was used to classify the writer’s gender and age based on the extracted features. We built an Arabic dataset named FSHS to analyse and test the proposed system. In the gender detection system, applying the automatic feature extraction method to the FSHS dataset produced accuracy rates of 84.9% and 82.2% using ResNet and GoogleNet, respectively. While the age detection system using the automatic feature extraction method achieved accuracy rates of 69.7% and 61.1% using ResNet and GoogleNet, respectively

show abstract

Section: Related Workmentioning

confidence: 99%

Transfer Learning to Detect Age From Handwriting

AL-Qawasmeh¹,

Suen²

2022

AAIML

View full text Add to dashboard Cite

show abstract

“…These machines are tuned by radial basis kernel functions. In [3] SVM classifier with polynomial kernel and the Gaussian radial basis function kernel is used. A tenfold cross-validation method is also used.…”

Section: Literature Reviewmentioning

confidence: 99%

Automatic Personality Analysis through Signatures

Khan¹

2019

IJRASET

View full text Add to dashboard Cite

Handwriting analysis or Graphology is the most widely used tool for personality analysis. Writing is a process in which the brain and muscles are involved. Each time a person writes a particular thing specific neuro-motor control is triggered and almost same pattern is generated. These neuro-motor controls are highly affected by age, behavior, drug addiction etc. That is why Signatures or handwriting are treated as behavioral biometric. Specific behavioral traits are associated with a specific signature pattern. These patterns can easily be decoded by skilled graphologists. This paper proposes an automated technique to identify some basic traits of the person on the basis of his/her signature. The proposed system uses basic signature traits like proportion, size, baseline, slanting and space to identify behavioral traits of the signer. Personality types are divided into four pairs of dominant traits. Each pair consist of two extremes. The signer is characterized on the basis of these dominant classes.

show abstract

“…The data set is assigned to a class which generates the maximum conditional posterior probability with available attributes as input using Bayes rule [15]. K-fold cross validation method is implemented to split the features extracted in the proposed model into training and testing set [16]. This method has an advantage that it makes full use of the limited sample dataset for classification so as to evaluate performance of proposed feature set for glioma grade identification.…”

Section: Classificationmentioning

confidence: 99%

Local Contrast based Texture features for Gliomas Grade Identification using Magnetic Resonance Images

Gupta¹

2019

IJATCSE

View full text Add to dashboard Cite

Gliomas are most common brain tumor in children and adults worldwide and accounts for 80% of all malignant tumors. In this work, we proposed a novel method for glioma grade classification using texture feature set extracted from T2-weighted magnetic resonance images (MRI). Gray-level co-occurrence matrix (GLCM) parameters are computed from local Optimal Oriented Pattern (LOOP) transformed images to differentiate low grade and high grade glioma. Classification is carried out using support vector machine (SVM), Naive Bayes and k-nearest neighbor (k-NN) classifier and their performance for glioma grade classification is accessed. SVM classifier outperforms other classifiers and achieved an accuracy of 95%, sensitivity of 93% and specificity of 100% for classifying gliomas using proposed LOOP transformed based GLCM texture features.

show abstract

Handwriting Classification Based on Support Vector Machine with Cross Validation

Cited by 16 publications

References 10 publications

Transfer Learning to Detect Age From Handwriting

Transfer Learning to Detect Age From Handwriting

Automatic Personality Analysis through Signatures

Local Contrast based Texture features for Gliomas Grade Identification using Magnetic Resonance Images

Contact Info

Product

Resources

About