Online Arabic handwriting recognition using continuous Gaussian mixture HMMS

doi:10.1109/ICIAS.2007.4658571

Home
/
Papers
/
Online Arabic handwriting recognition using continuous Gaussian mixture HMMS

Proceedings Article•DOI•

Online Arabic handwriting recognition using continuous Gaussian mixture HMMS

G. Al-Habian¹, Khaled Assaleh¹•Institutions (1)

American University of Sharjah¹

01 Nov 2007-pp 1183-1186

TL;DR: A recognizer structure aimed at recognizing online Arabic handwriting written in continuous form using hidden Markov models to model each stroke resulted in promising recognition rates, which is significantly better than currently available solutions.

read less

Abstract: In this paper, we present a recognizer structure aimed at recognizing online Arabic handwriting written in continuous form. The basic units of recognition used are strokes, which are sub-letter parts. To recognize strokes we used hidden Markov models (HMMs) to model each stroke. Decision logic was then used to interpret the output of stroke HMMs, converting their output into recognized-words. Data collected from six writers was used to validate the functionality of the system. Experimental simulation of the proposed system resulted in promising recognition rates (>75%), which is significantly better than currently available solutions.

...read moreread less

Citations

PDF

Open Access

More filters

Journal Article•DOI•

Online Arabic handwriting recognition: a survey

[...]

Najiba Tagougui¹, Monji Kherallah¹, Adel M. Alimi¹•Institutions (1)

University of Sfax¹

01 Sep 2013-International Journal on Document Analysis and Recognition

TL;DR: This survey is the first survey to focus on online Arabic handwriting recognition and provide recognition rates and descriptions of database used for the discussed approaches and is based on an extensive review of the literature.

...read moreread less

Abstract: Researches on handwriting recognition have known a great attention since it has been considered as a technological revolution in man-machines interfaces especially that handwriting has continued to persist as the most used mean of communication and recording information in day-to-day life. The challenging nature of handwriting recognition and segmentation has attracted the attention of researchers from academic and industry circles. The huge part of these researches deals with Latin and Chinese. Interest in Arabic script comes years later, and so the state of the art is less advanced. This survey describes the nature of this Arabic handwritten language and the basic concepts behind the recognition process. An overview of the state of the art of online Arabic handwriting recognition is presented. It is based on an extensive review of the literature in order to describe background in the field, discussion of the methods, and future research directions. It is the first survey to focus on online Arabic handwriting recognition and provide recognition rates and descriptions of database used for the discussed approaches.

...read moreread less

94 citations

Cites background or methods from "Online Arabic handwriting recogniti..."

...Combining online and offline preprocessing is also used in [46,47] and [48]....
[...]
...Whereas Al-Habian and Assaleh [47] present a recognizer structure aimed at recognizing online Arabic handwriting written in continuous form, the basic units of recognition used are strokes, which are subletter parts....
[...]
...Offline features were inspected by Al-Habian and Assaleh [47]....
[...]
...Elanwar et al. [51] Geometric features based on Feeman chain + segmentation-based approach using dynamic programming and template matching 317 words (1,814 characters), written by four writers for training 74 % word based 94 words (435 characters) written by other four writers for test 95.4 % character based Kherallah et al. [42] Modeling based on inflection point detection, the overlapped form of beta signals, and the elliptic arcs + beta-elliptical modeling + combining MLPNN + SOM + FKNN 30,000 Arabic digits 95.08 % Al-Taani and Hammad [46] Identifying the changes in the slope’s signs around zero + template matching 3,000 Arabic digits written by 100 persons 95 % Izadi et al. [38] Wavelet-based smoothing technique + Segmentationbased approach + DTW classifier 20 classes of paws with two and three characters for Persian script 89.4 % for two letters word 85 % for three letters word Mezghani et al. [35] + Bayes classification Zhu et al. tangents and histograms projection 528 characters of each letter from each of 22 writers for a total of 9,504 characters 92.61 % No diacritical points The training set contains 6,336 samples and the testing set 3,168 samples Sternby et al. [6] Template matching + using BLSTM algorithm, for dynamically treating the diacritical marks 1,578 samples of 66 Arabic words written by 40 persons Between 80 and 91 % Assaleh et al. [70] The motion information of the hand movement is projected onto two static AD images + video-based approach + KNN classifier Videos of 28 isolated Arabic letters Each letter was written eight times by two different users 97.77 % with polar ADs and 99.11 % for the two-tier-weighted AD scheme Daifallah et al. [37] Segmentation approach + HMM letters without marks or points 150 words 720 letters inside words 85.3–92.6 % for words 88.8– 97.2 % for letters Kherallah et al. [57] Combining visual coding and genetic algorithm 500 words written by 24 persons 97 % for isolated arabic words Saabni and El-Sana [44] Holistic approach + dynamic time warping classification....
[...]
...neural network [36,56,61], k-nearest neighbor [37,42], and other combination of techniques [47,62,75]....
[...]

Proceedings Article•DOI•

Online Arabic Handwriting Recognition Competition

[...]

Monji Kherallah¹, Najiba Tagougui¹, Adel M. Alimi¹, Haikal El Abed, Volker Märgner - Show less +1 more•Institutions (1)

University of Sfax¹

18 Sep 2011

TL;DR: The Online Arabic handwriting recognition competition held at ICDAR 2011 is described, with 3 groups with 5 systems participating in the competition and the most important characteristic of classification systems, the recognition rate.

...read moreread less

Abstract: Arabic script presents a challenge complexity and variability for handwriting recognition. The first on line Arabic Database called ADAB is known as a standard benchmark in the ICDAR competition of 2009. This paper describes the Online Arabic handwriting recognition competition held at ICDAR 2011. 3 groups with 5 systems are participating in the competition. The systems were tested on known data (sets 1 to 4) and on two test datasets which are unknown to all participants (set 5 and set 6). The systems are compared on the most important characteristic of classification systems, the recognition rate. Additionally, the relative speed of every system was compared. A short description of the participating groups, their systems, the experimental setup, and the performed results are presented.

...read moreread less

76 citations

Journal Article•DOI•

On-line Arabic handwriting recognition competition: ADAB database and participating systems

[...]

Haikal El Abed¹, Monji Kherallah², Volker Märgner¹, Adel M. Alimi²•Institutions (2)

Braunschweig University of Technology¹, University of Sfax²

01 Mar 2011-International Journal on Document Analysis and Recognition

TL;DR: This paper describes the on-line Arabic handwriting recognition competition held at tenth International Conference on Document Analysis and Recognition (ICDAR in Proceedings of the 10th international conference on document analysis and recognition, vol 3, pp 1388–1392, 2009).

...read moreread less

Abstract: This paper describes the on-line Arabic handwriting recognition competition held at tenth International Conference on Document Analysis and Recognition (ICDAR in Proceedings of the 10th international conference on document analysis and recognition, vol 3, pp 1388–1392, 2009). This first competition uses the so-called ADAB database with Arabic on-line handwritten words. At this first competition, 3 groups with 7 different systems have participated. The systems were tested on known data (training datasets made available for the participants, sets 1 to 3) and on one test dataset that is unknown to all participants (set 4). The systems are compared on the most important characteristic of classification systems, the recognition rate. Additionally, the relative speed of the different systems was compared. A short description of the participating groups, their systems, the experimental setup, and the performed results is presented.

...read moreread less

55 citations

Cites methods from "Online Arabic handwriting recogniti..."

...Based on the HMMs system, Al-Habian and Assaleh [17] discuss the use of feature vector extracted from a sliding window on the reconstituted image of the on-line text....
[...]

Journal Article•DOI•

Arabic Online Handwriting Recognition (AOHR): A Survey

[...]

Baligh Al-Helali¹, Sabri A. Mahmoud¹•Institutions (1)

King Fahd University of Petroleum and Minerals¹

29 Jun 2017-ACM Computing Surveys

TL;DR: This article comprehensively surveys Arabic Online Handwriting Recognition (AOHR), addressing the challenges posed by online handwriting recognition, including ligatures, dots and diacritic problems, online/offline touching of text, and geometric variations.

...read moreread less

Abstract: This article comprehensively surveys Arabic Online Handwriting Recognition (AOHR). We address the challenges posed by online handwriting recognition, including ligatures, dots and diacritic problems, online/offline touching of text, and geometric variations. Then we present a general model of an AOHR system that incorporates the different phases of an AOHR system. We summarize the main AOHR databases and identify their uses and limitations. Preprocessing techniques that are used in AOHR, viz. normalization, smoothing, de-hooking, baseline identification, and delayed stroke processing, are presented with illustrative examples. We discuss different techniques for Arabic online handwriting segmentation at the character and morpheme levels and identify their limitations. Feature extraction techniques that are used in AOHR are discussed and their challenges identified. We address the classification techniques of non-cursive (characters and digits) and cursive Arabic online handwriting and analyze their applications. We discuss different classification techniques, viz. structural approaches, Support Vector Machine (SVM), Fuzzy SVM, Neural Networks, Hidden Markov Model, Genetic algorithms, decision trees, and rule-based systems, and analyze their performance. Post-processing techniques are also discussed. Several tables that summarize the surveyed publications are provided for ease of reference and comparison. We summarize the current limitations and difficulties of AOHR and future directions of research.

...read moreread less

27 citations

Cites background or methods from "Online Arabic handwriting recogniti..."

...In Alijla and Kwaik [2012], they used the density, the aspect ratio, and character alignment ratio....
[...]
...In Alimi [1997], the segmentation is performed manually during the training phase....
[...]
...Recognition based on sub-character graphemes reduces the number of basic classes, as in Al-Habian and Assaleh [2007]. However, some effort is required to produce meaningful text from these graphemes....
[...]
...In Alijla and Kwaik [2012], they used the density, the aspect ratio, and character alignment ratio. In Ramzi and Zahary [2014], the extraction of offline features is accomplished over three steps: zoning, traversal, and determining the types of line segments. The feature vector is formed by combining the features of the zones. The features of each zone are the normalized length of each line type, the normalized area, Euler number, regional area, and eccentricity. A summary of the features used in some studies is given in Table IV. As shown in Table IV, different types of features are typically combined due to the shortcomings of each type individually. In Ramzi and Zahary [2014], several experiments with different types of features are conducted to select the best features....
[...]
...Post-processing is conducted in two steps in Al-Habian and Assaleh [2007]. First, rules are imposed on the letter shapes to exclude the recognized candidate letter shapes that are invalid for a corresponding position in a word....
[...]

Proceedings Article•DOI•

Segmentation techniques for online Arabic handwriting Recognition: A survey

[...]

Mustafa Ali Abuzaraida¹, Ahmed M. Zeki¹, Akram M. Zeki¹•Institutions (1)

International Islamic University Malaysia¹

01 Dec 2010

TL;DR: This paper presents and compares techniques that have been used to segment Arabic handwriting scripts in online recognition systems, and the structure and strategy of those reviewed techniques are explained.

...read moreread less

Abstract: This paper presents and compares techniques that have been used to segment Arabic handwriting scripts in online recognition systems. Those techniques attempt to segment cursive Arabic words into characters, or segment characters into small strokes that can be recognized via the recognition system. The structure and strategy of those reviewed techniques are explained in this article. The strengths and weaknesses of using these techniques will also be discussed.

...read moreread less

24 citations

Cites background or methods from "Online Arabic handwriting recogniti..."

...Also, AI-habian and Assaleh [5] presented a structured model for recognizing online Arabic handwriting written in continuous form based on Hidden Markov Models (HMMs) to recognize Arabic strokes....
[...]
...[5] G. AI-Habian, and K. Assaleh, "Online Arabic handwriting recognition using continuous Gaussian mixture HMMS, " International Conference on Intelligent and Advanced Systems, ICIAS 2007, Kuala Lumpur, Malaysia. vol: 1, page(s): 1183-1186....
[...]
...According to Al-habian and Assaleh [5], after acquiring the text via input device, a formatting sequence (x, y) was done to represent the text....
[...]

1
2
3
4
…

References

PDF

Open Access

More filters

Journal Article•DOI•

A tutorial on hidden Markov models and selected applications in speech recognition

[...]

Lawrence R. Rabiner¹•Institutions (1)

Bell Labs¹

01 Feb 1989

TL;DR: In this paper, the authors provide an overview of the basic theory of hidden Markov models (HMMs) as originated by L.E. Baum and T. Petrie (1966) and give practical details on methods of implementation of the theory along with a description of selected applications of HMMs to distinct problems in speech recognition.

...read moreread less

Abstract: This tutorial provides an overview of the basic theory of hidden Markov models (HMMs) as originated by L.E. Baum and T. Petrie (1966) and gives practical details on methods of implementation of the theory along with a description of selected applications of the theory to distinct problems in speech recognition. Results from a number of original sources are combined to provide a single source of acquiring the background required to pursue further this area of research. The author first reviews the theory of discrete Markov chains and shows how the concept of hidden states, where the observation is a probabilistic function of the state, can be used effectively. The theory is illustrated with two simple examples, namely coin-tossing, and the classic balls-in-urns system. Three fundamental problems of HMMs are noted and several practical techniques for solving these problems are given. The various types of HMMs that have been studied, including ergodic as well as left-right models, are described. >

...read moreread less

21,819 citations

Journal Article•DOI•

Online and off-line handwriting recognition: a comprehensive survey

[...]

Réjean Plamondon¹, Sargur N. Srihari²•Institutions (2)

École Normale Supérieure¹, University at Buffalo²

01 Jan 2000-IEEE Transactions on Pattern Analysis and Machine Intelligence

TL;DR: The nature of handwritten language, how it is transduced into electronic data, and the basic concepts behind written language recognition algorithms are described.

...read moreread less

Abstract: Handwriting has continued to persist as a means of communication and recording information in day-to-day life even with the introduction of new technologies. Given its ubiquity in human transactions, machine recognition of handwriting has practical significance, as in reading handwritten notes in a PDA, in postal addresses on envelopes, in amounts in bank checks, in handwritten fields in forms, etc. This overview describes the nature of handwritten language, how it is transduced into electronic data, and the basic concepts behind written language recognition algorithms. Both the online case (which pertains to the availability of trajectory data during writing) and the off-line case (which pertains to scanned images) are considered. Algorithms for preprocessing, character and word recognition, and performance with practical systems are indicated. Other fields of application, like signature verification, writer authentification, handwriting learning tools are also considered.

...read moreread less

2,653 citations

"Online Arabic handwriting recogniti..." refers background in this paper

...The difference between the two modes is that the online mode provides us with temporal features that are used to infer the dynamics of the writing....
[...]

Journal Article•DOI•

Offline Arabic handwriting recognition: a survey

[...]

L.M. Lorigo¹, Venu Govindaraju¹•Institutions (1)

State University of New York System¹

01 May 2006-IEEE Transactions on Pattern Analysis and Machine Intelligence

TL;DR: This paper is the first survey to focus on Arabic handwriting recognition and the first Arabic character recognition survey to provide recognition rates and descriptions of test data for the approaches discussed.

...read moreread less

Abstract: The automatic recognition of text on scanned images has enabled many applications such as searching for words in large volumes of documents, automatic sorting of postal mail, and convenient editing of previously printed documents. The domain of handwriting in the Arabic script presents unique technical challenges and has been addressed more recently than other domains. Many different methods have been proposed and applied to various types of images. This paper provides a comprehensive review of these methods. It is the first survey to focus on Arabic handwriting recognition and the first Arabic character recognition survey to provide recognition rates and descriptions of test data for the approaches discussed. It includes background on the field, discussion of the methods, and future research directions.

...read moreread less

503 citations

Proceedings Article•DOI•

HMM based approach for handwritten arabic word recognition using the IFN/ENIT - database

[...]

Mario Pechwitz¹, V. Maergner¹•Institutions (1)

Braunschweig University of Technology¹

03 Aug 2003

TL;DR: An offline recognition system for Arabic handwrittenwords is presented and achieves maximal recognitionrates of about 89% on a word level using the new IFN/ENIT - database of handwritten Arabicwords.

...read moreread less

Abstract: An offline recognition system for Arabic handwrittenwords is presented. The recognition system is based ona semi-continuous 1-dimensional HMM. From each binaryword image normalization parameters were estimated. Firstheight, length, and baseline skew are normalized, then featuresare collected using a sliding window approach. Thispaper presents these methods in more detail. Some parameterswere modified and the consequent effect on the recognitionresults are discussed. Significant tests were performedusing the new IFN/ENIT - database of handwritten Arabicwords. The comprehensive database consists of 26459Arabic words (Tunisian town/village names) handwrittenby 411 different writers and is free for non-commercial research.In the performed tests we achieved maximal recognitionrates of about 89% on a word level.

...read moreread less

167 citations

"Online Arabic handwriting recogniti..." refers background in this paper

...However, in online recognition the input is being captured sample by sample from the writer while he/she is writing....
[...]

Journal Article•DOI•

Handwritten Farsi (Arabic) word recognition: a holistic approach using discrete HMM

[...]

Mehdi Dehghan¹, Karim Faez¹, Majid Ahmadi², Malayappan Shridhar³•Institutions (3)

Amirkabir University of Technology¹, University of Windsor², University of Michigan³

01 May 2001-Pattern Recognition

TL;DR: A holistic system for the recognition of handwritten Farsi/Arabic words using right–left discrete hidden Markov models (HMM) and Kohonen self-organizing vector quantization is presented.

...read moreread less

153 citations