Combining Deep and Ad-hoc Solutions to Localize Text Lines in Ancient Arabic Document Images

Mechi, Olfa; Mehri, Maroua; Ingold, Rolf; Amara, Najoua Essoukri Ben

doi:10.1109/icpr48806.2021.9412562

Cited by 3 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNN models have proven effective in AHR, with a primary focus on tasks like digit, character, and word recognition. For segmentation challenges, FCN, a combination of CNN and AutoEncoder, is commonly employed for its proficiency in handling the challenges of this task [11,29,30,[33][34][35][36][37]. Results vary across recognition tasks, showcasing the inherent difficulty of each problem.…”

Section: Highlights and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

CNN-based Methods for Offline Arabic Handwriting Recognition: A Review

El Khayati,

Kich,

Taouil

2024

Neural Process Lett

View full text Add to dashboard Cite

Arabic Handwriting Recognition (AHR) is a complex task involving the transformation of handwritten Arabic text from image format into machine-readable data, holding immense potential across various applications. Despite its significance, AHR encounters formidable challenges due to the intricate nature of Arabic script and the diverse array of handwriting styles. In recent years, Convolutional Neural Networks (CNNs) have emerged as a pivotal and promising solution to address these challenges, demonstrating remarkable performance and offering distinct advantages. However, the dominance of CNNs in AHR lacks a dedicated comprehensive review in the existing literature. This review article aims to bridge the existing gap by providing a comprehensive analysis of CNN-based methods in AHR. It covers both segmentation and recognition tasks, delving into advancements in network architectures, databases, training strategies, and employed methods. The article offers an in-depth comparison of these methods, considering their respective strengths and limitations. The findings of this review not only contribute to the current understanding of CNN applications in AHR but also pave the way for future research directions and improved practices, thereby enriching and advancing this critical domain. The review also aims to uncover genuine challenges in the domain, providing valuable insights for researchers and practitioners.

show abstract

Section: Highlights and Discussionmentioning

confidence: 99%

“…The adaptive U-Net was integrated with traditional analysis techniques in another study conducted by the same authors [37], to boost performance. The U-Net was utilized to identify the primary area covering the text core known as X-height.…”

Section: Segmentationmentioning

confidence: 99%

CNN-based Methods for Offline Arabic Handwriting Recognition: A Review

El Khayati,

Kich,

Taouil

2024

Neural Process Lett

View full text Add to dashboard Cite

show abstract

“…125 Arabic document images Accuracy=96% [25] A graph-based technique to detect touching and prox-imity errors + a refinement operation using Expectation Maximization (EM) Private datasets of 125 Ara-bic document images with 1974 text-lines F1=98.76% [26] A smearing technique based on morphological dilation with a dynamic adaptive mask CENPARMI Arabic handwrit-ten documents (Section IV-A) Precision =96.3% [27] the horizontal projection profile (HPP) Benchmarking datasets of the AHDB extraction rate=84.8% [28] Hough transform approach preceded by a novel method based on skeletonization in the post-processing stage IFN/ENIT and Arabic Hand-writing Database: AHDB Accuracies=97.4% and 98.9% [29] A deep learning Architecture (RU-net). KHATT Accuracy = 96.7% [6] A deep neural network called AR2U-Net based on the U-Net model BADAM Precision = 93.2% [30] Hybrid method (a deep network (U-Net architecture) with classical image analysis techniques).…”

Section: Author the Segmentation Techniquementioning

confidence: 99%

“…Mechi, Olfa, et al (2021) [30] introduced a hybrid method that combines a U-Net deep network with traditional document image analysis techniques. For instance, connected component analysis and modified RLSA were integrated to localize text lines in diverse datasets of Handwritten Arabic documents, encompassing both public and private sources.…”

Section: Ltp (Local Touching Patches) Databasementioning

confidence: 99%

A Survey on Text-Line Segmentation in Arab Historical Manuscripts

Djaghbellou,

Attıa,

Bouzıane

2024

International Journal of Informatics and Applied Mathematics

View full text Add to dashboard Cite

The segmentation process entails dividing or decomposing the entire document image into segments or lines. This technique serves as a fundamental step in developing any writing or optical character recognition system. However, numerous existing segmentation schemes encounter challenges when dealing with specific script styles, like ancient or historical Arabic writing found in ancient manuscripts. which possesses unique characteristics. These characteristics include inclined text lines, overlapping letters, diacritic marks, decorative elements, variable letter forms, and ligatures (combinations of two or more letters merged to form a single connected shape).Thus, in this paper we present a thorough survey of the field. The survey is composed of two segments. The first segment provides a concise overview of the historical Arabic documents. The second, which serves as the primary segment, focuses on the crucial step of handwritten document recognition, specifically segmentation. A detailed and systematic overview of the various approaches to segmentation, including different levels, employed for extracting handwritten Arabic text-lines, is outlined. Subsequently, a literature study is conducted to review and analyze proposed works in this area.

show abstract