article · International Journal of Advanced Computer Science and Applications
An algorithm combining deep convolutional neural networks and support vector machines provides a method for recognising and classifying handwritten Arabic letters and characters. The approach addresses recognition by calculating the similarity between input characters and pre-stored templates through fully connected deep neural networks and dropout support vector machines. To manage the challenges associated with multi-stroke Arabic characters, the system incorporates a K-means clustering approach that groups similar characters effectively. Experimental testing evaluates system performance through correct classification rates and error classification rates. The combined method achieves a correct classification rate of 95.07 percent and an error classification rate of 4.93 percent. These results demonstrate the algorithm's capability to recognise, identify, and verify handwritten Arabic inputs against existing state of the art techniques.
Automating the recognition of handwritten Arabic script is vital for natural language processing and computer vision systems. Arabic handwriting presents distinct technical challenges due to variations in strokes and character shapes. High recognition accuracy supports improved document digitisation and text analysis for Arabic-language applications.
The algorithm demonstrates applied and tested character recognition capabilities, achieving high accuracy in laboratory benchmarks. Potential applications include automated document processing, form reading, and vehicle license plate recognition systems for Arabic script users. However, because testing appears limited to experimental template comparisons, practical commercial deployment would require integration into end-user optical character recognition software and testing on varied, unconstrained real-world documents.
AI-generated from the published abstract. Always read the original work before citing.
Recognition of Arabic characters is essential for natural language processing and computer vision fields. The need to recognize and classify the handwritten Arabic letters and characters are essentially required. In this paper, we present an algorithm for recognizing Arabic letters and characters based on using deep convolution neural networks (DCNN) and support vector machine (SVM). This paper addresses the problem of recognizing the Arabic handwritten characters by determining the similarity between the input templates and the pre-stored templates using both fully connected DCNN and dropout SVM. Furthermore, this paper determines the correct classification rate (CRR) depends on the accuracy of the corrected classified templates, of the recognized handwritten Arabic characters. Moreover, we determine the error classification rate (ECR). The experimental results of this work indicate the ability of the proposed algorithm to recognize, identify, and verify the input handwritten Arabic characters. Furthermore, the proposed system determines similar Arabic characters using a clustering algorithm based on the K-means clustering approach to handle the problem of multi-stroke in Arabic characters. The comparative evaluation is stated and the system accuracy reached 95.07% CRR with 4.93% ECR compared with the state of the art.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.14569/ijacsa.2020.0110819
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
