Transfer Learning to Detect Age From Handwriting

Abstract

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

Enhancing Age Estimation from Handwriting: A Deep Learning Approach with Attention Mechanisms

“…They divided the KHATT dataset into four age groups according to official classification and achieved an accuracy rate of 64.4%. In addition, Najla AL-Qawasmeh et al [11] extracted hand-written features from a self-built Arabic dataset and used ResNet and GoogleNet to predict the author's age with accuracy rates of 69.7% and 61.1%, respectively [29]. However, simply converting the neural network to hand-written age recognition may lead to lower accuracy because of the complexity of hand-written features, and a single neural network may ignore some important features.…”

“…ResNet offers an effective solution to the vanishing gradient problem by introducing skip connections to reduce the depth of the network. Even so, ResNet is not without its drawbacks, such as high computational costs and susceptibility to overfitting [11]. Furthermore, research indicates that utilizing the GoogleNet and ResNet architectures for automated feature extraction, coupled with SVM classification, results in improved performance for handwritten age classification, although the classification accuracy remains relatively low [11].…”