Experiment study on utilizing convolutional neural networks to recognize historical Arabic handwritten text

Alaasam, Reem; Kurar, Berat; Kassis, Majeed; El-Sana, Jihad

doi:10.1109/asar.2017.8067773

Cited by 12 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different public handwritten document image datasets have been created and presented to resolve various document image challenges such as text line segmentation [7], word spotting [8], writer identification [9], digit and character segmentation and recognition [10][11][12], binarization [13], and a variety of other challenges [14][15][16]. These datasets enable researchers to develop automated and computationally efficient algorithms.…”

Section: Review Of Related Public Datasetsmentioning

confidence: 99%

SHIBR—The Swedish Historical Birth Records: a semi-annotated dataset

Cheddad

Kusetoğulları

Hilmkil³

et al. 2021

Neural Comput & Applic

View full text Add to dashboard Cite

This paper presents a digital image dataset of historical handwritten birth records stored in the archives of several parishes across Sweden, together with the corresponding metadata that supports the evaluation of document analysis algorithms’ performance. The dataset is called SHIBR (the Swedish Historical Birth Records). The contribution of this paper is twofold. First, we believe it is the first and the largest Swedish dataset of its kind provided as open access (15,000 high-resolution colour images of the era between 1800 and 1840). We also perform some data mining of the dataset to uncover some statistics and facts that might be of interest and use to genealogists. Second, we provide a comprehensive survey of contemporary datasets in the field that are open to the public along with a compact review of word spotting techniques. The word transcription file contains 17 columns of information pertaining to each image (e.g., child’s first name, birth date, date of baptism, father's first/last name, mother’s first/last name, death records, town, job title of the father/mother, etc.). Moreover, we evaluate some deep learning models, pre-trained on two other renowned datasets, for word spotting in SHIBR. However, our dataset proved challenging due to the unique handwriting style. Therefore, the dataset could also be used for competitions dedicated to a large set of document analysis problems, including word spotting.

show abstract

Section: Review Of Related Public Datasetsmentioning

confidence: 99%

SHIBR—The Swedish Historical Birth Records: a semi-annotated dataset

Cheddad

Kusetoğulları

Hilmkil³

et al. 2021

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…Among notable studies on analysis of Arabic manuscripts, [7] propose a 5-layered convolutional neural network to recognize 68 classes of Arabic subwords extracted from historical collections. The network comprises 2 convolutional and 3 fully connected layers and reports a recognition rate of 81%.…”

Section: Handwriting Recognition In Historical Arabic Documentsmentioning

confidence: 99%

Subword Recognition in Historical Arabic Documents using C-GRUs

Hassen¹,

Al-Madeed²,

Bouridane³

2021

TEM Journal

View full text Add to dashboard Cite

The recent years have witnessed an increased tendency to digitize historical manuscripts that not only ensures the preservation of these collections but also allows researchers and end-users’ direct access to these images. Recognition of Arabic handwriting is challenging due to the highly cursive nature of the script and other challenges associated with historical documents (degradation etc.). This paper presents an end-to-end system to recognize Arabic handwritten sub words in historical documents. More specifically, we introduce a hybrid CNN-GRU model where the shallow convolutional network learns robust feature representations while the GRU layers carry out the sequence modelling and generate the transcription of the text. The proposed system is evaluated on two different datasets, IBN SINA and VML-HD reporting recognition rates of 96.10% and 98.60% respectively. A comparison with existing techniques evaluated on the same datasets validates the effectiveness of our proposed model in characterizing Arabic subwords.

show abstract