Abstract
Arabic and Hindi handwritten numeral detection and classification is one of the most popular fields in the automation research. It has many applications in different fields. Automatic detection and automatic classification of handwritten numerals have persistently received attention from researchers around the world due to the robotic revolution in the past decades. Therefore, many great efforts and contributions have been made to provide highly accurate detection and classification methodologies with high performance. In this paper, we propose a two-stage methodology for the detection and classification of Arabic and Hindi handwritten numerals. The classification was based on convolutional neural networks (CNNs). The first stage of the methodology is the detection of the input numeral to be either Arabic or Hindi. The second stage is to detect the input numeral according to the language it came from. The simulation results show very high performance; the recognition rate was close to 100%.
Highlights
Automatic recognition is widely applied in many aspects; such as face recognition, fingerprint recognition, and numerals recognition
We employed convolutional neural networks (CNNs) for the offline recognition of Arabic and Hindi handwritten decimal numbers and through different number of scenarios and experiments, we demonstrated that very high recognition rates can be achieved
In their work [13], Choudhary et al used a supervised learning technique based on the artificial neural network (ANN) for offline handwritten numeral recognition, where they employed a multilayered perceptron (MLP) with one hidden layer
Summary
Automatic recognition is widely applied in many aspects; such as face recognition, fingerprint recognition, and numerals recognition. There are still some daily activities and tasks that depend on traditional methods of communication, such as using paper and pen. Handwritten digit recognition is one of the most successful applications of automatic pattern recognition either on-line or off-line. Most of such these applications were performed on Arabic digits, because it is the most known numbering system in the world. In our survey on related work about handwritten numeral recognition, we encountered few studies employing various classification techniques. In their work [13], Choudhary et al used a supervised learning technique based on the artificial neural network (ANN) for offline handwritten numeral recognition, where they employed a multilayered perceptron (MLP) with one hidden layer. The drawback of this work is the small-sized data set with very few samples
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call