Mohammed A. Al-Qodah
Papers
1
Total Citations
22
H-Index
1
About
Mohammed A. Al-Qodah is a researcher at the forefront of applying deep learning to document analysis and pattern recognition, with a particular focus on handwritten numeral recognition for Arabic and Hindi scripts. His most cited work, "Recognition of Handwritten Arabic and Hindi Numerals Using Convolutional Neural Networks" (2021, 22 citations), addresses a critical challenge in automation: the reliable detection and classification of handwritten digits, which has wide-ranging applications in banking, postal services, and digital archiving. By leveraging convolutional neural networks, Al-Qodah has contributed to bridging the gap between traditional script recognition and modern AI-driven approaches, demonstrating how deep architectures can handle the variability and complexity inherent in handwritten numerals. His research not only advances the field of optical character recognition but also underscores the importance of developing robust systems for non-Latin scripts, which have historically received less attention. Through his work, Al-Qodah has established himself as a key contributor to the growing body of knowledge on automated handwriting analysis, offering practical solutions that enhance accuracy and efficiency in real-world applications.
Research Focus
Key Achievements
Top Papers
- 1