Deep Learning-Based Child Handwritten Arabic Character Recognition and Handwriting Discrimination

Abstract

Handwritten Arabic character recognition has received increasing research interest in recent years. However, as of yet, the majority of the existing handwriting recognition systems have only focused on adult handwriting. In contrast, there have not been many studies conducted on child handwriting, nor has it been regarded as a major research issue yet. Compared to adults’ handwriting, children’s handwriting is more challenging since it often has lower quality, higher variation, and larger distortions. Furthermore, most of these designed and currently used systems for adult data have not been trained or tested for child data recognition purposes or applications. This paper presents a new convolution neural network (CNN) model for recognizing children’s handwritten isolated Arabic letters. Several experiments are conducted here to investigate and analyze the influence when training the model with different datasets of children, adults, and both to measure and compare performance in recognizing children’s handwritten characters and discriminating their handwriting from adult handwriting. In addition, a number of supplementary features are proposed based on empirical study and observations and are combined with CNN-extracted features to augment the child and adult writer-group classification. Lastly, the performance of the extracted deep and supplementary features is evaluated and compared using different classifiers, comprising Softmax, support vector machine (SVM), k-nearest neighbor (KNN), and random forest (RF), as well as different dataset combinations from Hijja for child data and AHCD for adult data. Our findings highlight that the training strategy is crucial, and the inclusion of adult data is influential in achieving an increased accuracy of up to around 93% in child handwritten character recognition. Moreover, the fusion of the proposed supplementary features with the deep features attains an improved performance in child handwriting discrimination by up to around 94%.

Dhad—A Children’s Handwritten Arabic Characters Dataset for Automated Recognition

“…A custom CNN model was developed, motivated from the literature [4,5,[13][14][15] to investigate the performance of a simpler network trained from scratch for the children's handwritten character classification. The model is particularly tailored for grayscale images with a size of 32 × 32 pixels (Figure 1).…”

“…Meanwhile, recall or sensitivity measures the ratio of correctly classified positive examples to the true positive examples (4). The F1 score is calculated as the harmonic mean of the precision and recall; thus, it combines both precision and recall in a single value (5). The Jaccard Similarity Index (often referred to simply as J-Index) is a measure of how close the predicted labels are to the actual labels (6).…”

“…In Experiment Two, a custom CNN model, drawing inspiration from the existing literature [4,5,[13][14][15], was meticulously crafted and subsequently trained on both the Dhad and Hijja datasets. A detailed analysis of the model's training dynamics, as depicted in Figure 13, offers invaluable insights into its performance and adaptability.…”

“…The significance of addressing the issue of Arabic handwritten recognition, particularly concerning children, arises from the increasing integration of technology in their educational and recreational activities. The ubiquitous use of smartphones and tablet devices by children, employing touchscreens and styluses for various purposes, including handwriting, underscores the need for automated recognition techniques tailored to the unique characteristics of children's handwriting [4][5][6].…”