Generating an Arabic Calligraphy Text Blocks for Global Texture Analysis (original) (raw)

A study of feature extraction for Arabic calligraphy characters recognition

International Journal of Electrical and Computer Engineering (IJECE), 2024

Optical character recognition (OCR) is one of the widely used pattern recognition systems. However, the research on ancient Arabic writing recognition has suffered from a lack of interest for decades, despite the availability of thousands of historical documents. One of the reasons for this lack of interest is the absence of a standard dataset, which is fundamental for building and evaluating an OCR system. In 2022, we published a database of ancient Arabic words as the only public dataset of characters written in Al-Mojawhar Moroccan calligraphy. Therefore, such a database needs to be studied and evaluated. In this paper, we explored the proposed database and investigated the recognition of Al-Mojawhar Arabic characters. We studied feature extraction by using the most popular descriptors used in Arabic OCR. The studied descriptors were associated with different machine learning classifiers to build recognition models and verify their performance. In order to compare the learned and handcrafted features on the proposed dataset, we proposed a deep convolutional neural network for character recognition. Regarding the complexity of the character shapes, the results obtained were very promising, especially by using the convolutional neural network model, which gave the highest accuracy score.

Fast learning neural network based on texture for Arabic calligraphy identification

Indonesian Journal of Electrical Engineering and Computer Science, 2021

Arabic calligraphy is considered a sort of Arabic writing art where letters in Arabic can be written in various curvy or segments styles. The efforts of automating the identification of Arabic calligraphy by using artificial intelligence were less comparing with other languages. Hence, this article proposes using four types of features and a single hidden layer neural network for training on Arabic calligraphy and predicting the type of calligraphy that is used. For neural networks, we compared the case of nonconnected input and output layers in extreme learning machine ELM and the case of connected input-output layers in FLN. The prediction accuracy of fast learning machine FLN was superior comparing ELM that showed a variation in the obtained accuracy.

High Performance Layout Analysis of Arabic and Urdu Document Images

2011

Abstract Text-lines extraction and their reading order determination is an important step in optical character recognition (OCR) systems. Research in OCR of Arabic script documents has primarily focused on character recognition and therefore most of researchers use primitive methods like projection profile analysis for text-line extraction. Although projection methods achieve good accuracy on clean, skew corrected documents, their performance drops under challenging situations (border noise, skew, complex layouts).

CREATION OF ARAB GRAPHIC WRITINGS RECOGNITION PROGRAM

IASET, 2021

The most effective results in the processing and recognition of images are achieved through the development of information technology, the introduction of new technologies. The TensorFlow library capabilities in the python programming environment are huge in getting effective results. It describes how to use open data sets to recognize Arabic graphics and to form datasets for additional letters for old Uzbek and Farsi text letters. Examples, advantages and analysis of the results obtained by the TensorFlow platform to perform calculations with python are given. The efficacy and mode of use of the convolutional neural network are described. Results were obtained from the use of open data sets via www.kaggle.com. The most effective methods of recognizing the given Arabic text are used, and only the results obtained are described, without the algorithms given in the references. CNN created a model for the data set letters, based on which the results were 90% recognizable.