An Efficient Language-Independent Multi-Font OCR for Arabic Script

Abstract

Optical Character Recognition (OCR) is the process of extracting digitized text from images of scanned documents. While OCR systems have already matured in many languages, they still have shortcomings in cursive languages with overlapping letters such as the Arabic language. This paper proposes a complete Arabic OCR system that takes a scanned image of Arabic Naskh script as an input and generates a corresponding digital document. Our Arabic OCR system consists of the following modules: Pre-processing, Word-level Feature Extraction, Character Segmentation, Character Recognition, and Post-processing. This paper also proposes an improved font-independent character segmentation algorithm that outperforms the state-of-the-art segmentation algorithms. Lastly, the paper proposes a neural network model for the character recognition task. The system has experimented on several open Arabic corpora datasets with an average character segmentation accuracy 98.06%, character recognition accuracy 99.89%, and overall system accuracy 97.94% achieving outstanding results compared to the state-of-the-art Arabic OCR systems.

Optical Recognition System of Non-Dotted Arabic Letters

“…The accuracy for the letters Aeen, Taa, Haa, Laam, and Waaw is perfect and has reached 100% to classify in sizes from 14 to 72 for all fonts. The small font sizes (8)(9)(10)(11)(12)(13)(14) and the accuracy range between 60-90% in all Arabic fonts Daal letter classification accuracy is in the range of 30-80% for sizes 8-14 and 90-100% for sizes 24-72. Raa letter classification accuracy is 20-70% for sizes (8)(9)(10)(11)(12)(13)(14)(15)(16) and 90% for sizes to all Arabic fonts.…”

“…Hussein Osman et al (2020) [12] Present a neural network model. The system has been tested on several open Arabic corpora datasets and has achieved outstanding results when compared to state-of-the-art Arabic OCR systems, with an average character segmentation accuracy of 98.06%, character recognition accuracy of 99.89%, and an overall system accuracy of 97.94%.…”

Visual News Ticker Surveillance Approach from Arabic Broadcast Streams

“…Less number of classes with de-shaped samples up to a certain limit (per class) is a way towards model simplicity. Reference [23] also used a heuristic method for segmentation with previously mentioned limitations. Such contemporary methods may work on clean data that is unfeasible for applications like Arabic news ticker recognition.…”