Arabic handwritten document preprocessing and recognition

Chammas, Edgard; Mokbel, Chafic; Likforman-Sulem, Laurence

doi:10.1109/icdar.2015.7333802

Cited by 7 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section is devoted to shedding light on numerous articles that introduced many methods to improve the efficiency of recognizing Arabic characters. Such methods include LHT [6], [7], [8], [ 9], [ 10] , HMM [11], [12], [13], [14], histogram with Gabor filter [15], histogram with projection profile [16], [17], Otsu's model [9], [17], [18], heuristic rules differentiating [19], discrete cosine transform [20], parallel thinning algorithm [21], artificial immune system [22], and/or dynamic Bayesian network [23]. In addition, morphological algorithms [18] were applied to estimate document skew angles using the IFN/ENIT database.…”

Section: Related Workmentioning

confidence: 99%

Fast Technique to Recognize Closed Characters in Arabic Handwriting

Kandeel

2023

MSA Engineering Journal

View full text Add to dashboard Cite

Considering the distinctive features and characteristics of Arabic scripts, recognizing handwritten Arabic characters is still widely open as a major experimental task, which is not easy to overcome. This study attempts to develop a fast and effective technique for recognizing this difficult type of written script by using an iterative algorithm to extract closed Arabic characters. Some Arabic characters have circles that may be blurred, incomplete, unformed, or distorted. In addition to ligatures with different shapes, the technique is based on the development of a proper Circular Hough Transform. This study used IFN/ENIT, which is a standard database for extracting closed Arabic characters as designed in classes. The first class is closed blurred circles ‫,و(‬ ‫ع‬ , ‫م‬ ‫.)ق,‬ The second class is unformed circles ( ‫ة‬ , ‫ع‬ ‫.)ق,‬ The third one is incomplete circles ‫ض(‬ ‫ص,‬ ‫ظ,‬ , ‫ط‬ ‫.)ه,ة,‬ Finally, the fourth class is distorted circles ( ‫ظ‬ ‫ط,‬ ). This methodology achieved an outstanding accuracy of approximately 96.67%, a very interesting work for the total four classes related to the 11 closed Arabic characters (out of the 28 characters of the Arabic alphabet)..

show abstract

Section: Related Workmentioning

confidence: 99%

Fast Technique to Recognize Closed Characters in Arabic Handwriting

Kandeel

2023

MSA Engineering Journal

View full text Add to dashboard Cite

show abstract

“…As for Arabic language, major contributions have already been made in the conventional field of printed and handwritten OCR systems [7,10]. Much progress of such systems has been triggered thanks to the availability of public datasets.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Several techniques have been proposed in the conventional field of Arabic OCR in scanned documents [7][8][9][10]. However, few attempts have been made on the development of detection and recognition systems for overlaid text in Arabic news video [11][12][13].…”

mentioning

confidence: 99%

Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames

et al. 2018

View full text Add to dashboard Cite

Abstract:Recognizing texts in video is more complex than in other environments such as scanned documents. Video texts appear in various colors, unknown fonts and sizes, often affected by compression artifacts and low quality. In contrast to Latin texts, there are no publicly available datasets which cover all aspects of the Arabic Video OCR domain. This paper describes a new well-defined and annotated Arabic-Text-in-Video dataset called AcTiV 2.0. The dataset is dedicated especially to building and evaluating Arabic video text detection and recognition systems. AcTiV 2.0 contains 189 video clips serving as a raw material for creating 4063 key frames for the detection task and 10,415 cropped text images for the recognition task. AcTiV 2.0 is also distributed with its annotation and evaluation tools that are made open-source for standardization and validation purposes. This paper also reports on the evaluation of several systems tested under the proposed detection and recognition protocols.

show abstract

“…We have selected to employ hidden Markov models which have been successfully applied to a number of diverse problems including gesture recognition [36][37][38], speech recognition [39], handwriting recognition [38,40], musical score recognition [41], and optical character recognition [10,[42][43][44]. The steps of feature extraction from ligature clusters and subsequent training are discussed in the following subsections.…”

Section: Ligature Clusteringmentioning

confidence: 99%

Segmentation-free optical character recognition for printed Urdu text

Din

Siddiqi

Khalid

et al. 2017

J Image Video Proc.

View full text Add to dashboard Cite

This paper presents a segmentation-free optical character recognition system for printed Urdu Nastaliq font using ligatures as units of recognition. The proposed technique relies on statistical features and employs Hidden Markov Models for classification. A total of 1525 unique high-frequency Urdu ligatures from the standard Urdu Printed Text Images (UPTI) database are considered in our study. Ligatures extracted from text lines are first split into primary (main body) and secondary (dots and diacritics) ligatures and multiple instances of the same ligature are grouped into clusters using a sequential clustering algorithm. Hidden Markov Models are trained separately for each ligature using the examples in the respective cluster by sliding right-to-left the overlapped windows and extracting a set of statistical features. Given the query text, the primary and secondary ligatures are separately recognized and later associated together using a set of heuristics to recognize the complete ligature. The system evaluated on the standard UPTI Urdu database reported a ligature recognition rate of 92% on more than 6000 query ligatures.

show abstract

Arabic handwritten document preprocessing and recognition

Cited by 7 publications

References 11 publications

Fast Technique to Recognize Closed Characters in Arabic Handwriting

Fast Technique to Recognize Closed Characters in Arabic Handwriting

Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames

Segmentation-free optical character recognition for printed Urdu text

Contact Info

Product

Resources

About