Abstract
Handwriting recognition for computer systems has been in research for a long time, with different researchers having an extensive variety of methods at their disposal. The problem is that most of these experiments are done in English, as it is the most spoken language in the world. But other languages such as Arabic, Mandarin, Spanish, French, and Russian also need research done on them since there are millions of people who speak them. In this work, recognizing and developing Arabic handwritten characters is proposed by cleaning the state-of-the-art Arabic dataset called Hijaa, developing Conventional Neural Network (CNN) with a hybrid model using Support Vector Machine (SVM) and eXtreme Gradient Boosting (XGBoost) classifiers. The CNN is used for feature extraction of the Arabic character images, which are then passed on to the Machine Learning classifiers. A recognition rate of up to 96.3% for 29classes is achieved, far surpassing the already state-of-the-art results of the Hijaa dataset.
Highlights
Handwritten language forms a timeless and inevitable aspect of human life
Conventional Neural Network (CNN) trained with backpropagation and cannot be directly trained with the Machine Learning (ML) classifier
The same CNN was used to experiment on the Arabic Handwritten Characters Dataset (AHCD) dataset and it achieved an accuracy of 97%, which shows that at that time, the Hijja dataset was imbalanced and needed to be reevaluated
Summary
No matter how digital the world becomes, handwritten language will always remain. Even though the world is moving to a digital era, there are still some scenarios where the use of paper and pen cannot be avoided. Character recognition technologies provide the users an automatic mechanism for recognizing the text on the image and converting the characters to their corresponding digital format. They are used in many verification applications, e.g., verifying official documents and bank cheques and helping visually impaired people read, e.g., reading paper currency or street signs. Character recognition system can be used to read both typed and handwritten scripts. The handwriting varies, especially in cursive script, where the writers' handwritten characters' size and style vary. Handwriting recognition is considered a more difficult task in computer vision [1]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
