W-TSV: Weighted topological signature vector for lexicon reduction in handwritten Arabic documents

Chherawala, Youssouf; Cheriet, Mohamed

doi:10.1016/j.patcog.2012.02.030

Cited by 18 publications

(10 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The Malay cheque word (MCW) dictionary was elaborated upon the one implemented by [15] to include all common Malay words. The resulting MCW dictionary enabled surges in the obtained accuracies of the proposed system's output, which supports the understanding that such a generalized dictionary would be necessary to scale up this system to even bigger applications [22]. The word recognition step essentially relies on the lexical word classification (LWC) method, which was applied twice in this study.…”

Section: Lexical Word Classification (Lwc)supporting

confidence: 65%

A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: study case on Malay word recognition

Al-Boeridi¹,

Ahmad

Koh

2015

Neural Comput & Applic

View full text Add to dashboard Cite

An off-line handwriting recognition (OFHR) system is a computerized system that is capable of intelligently converting human handwritten data extracted from scanned paper documents into an equivalent text format. This paper studies a proposed OFHR for Malaysian bank cheques written in the Malay language. The proposed system comprised of three components, namely a character recognition system (CRS), a hybrid decision system and lexical word classification system. Two types of feature extraction techniques have been used in the system, namely statistical and geometrical. Experiments show that the statistical feature is reliable, accessible and offers results that are more accurate. The CRS in this system was implemented using two individual classifiers, namely an adaptive multilayer feed-forward back-propagation neural network and support vector machine. The results of this study are very promising and could generalize to the entire Malay lexical dictionary in future work toward scaled-up applications.

show abstract

Section: Lexical Word Classification (Lwc)supporting

confidence: 65%

A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: study case on Malay word recognition

Al-Boeridi¹,

Ahmad

Koh

2015

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…When the pixel at (2,7) is scanned, it is found that does not exist in any list available till now (i.e., dummy list and C1) hence a new list C2 is created and the coordinates (2,7) are stored in C2. Again, the 8-neighborhood of pixel is traced and coordinates (3,7) are stored in the list C2. Moving on to the pixel at (5,7) it is again found that it does not exist in any list hence a new list C3 is created and the coordinates of the current pixel; that is (5,7) and of the neighboring foreground pixels (5,6) and (6,6) are stored in C3.…”

Section: Methodsmentioning

confidence: 99%

“…Moving on to the pixel at (5,7) it is again found that it does not exist in any list hence a new list C3 is created and the coordinates of the current pixel; that is (5,7) and of the neighboring foreground pixels (5,6) and (6,6) are stored in C3. The algorithm proceeds to the pixel at (7,7). It is found that this pixel is already stored in C1.…”

Section: Methodsmentioning

confidence: 99%

“…C1={(5,10), (4,9), (5,9), (6,10), (7,9), (7,8), (8,9), (7,7), (5,7), (5,8), (6,6), (7,6), (4,5), (2,5), (3,5)} , C2={(2,7), (3,7)} , C3={(9,7), (10,6), (10,5), (9,4), (8,4), (8,3)} and C4={(6,4), (6,3), (6,2).…”

Section: Methodsunclassified

“…Number of PAWs, along with number and position of dots, were used as inputs to a lexicon pruning method in [8]. A lexicon-reduction strategy for Arabic documents based on the structure of Arabic sub-word shapes which is described by their topology is introduced in [7].There exist few attempts in the literature which aimed at segmenting the Arabic word/ text line into the composing sub-words. Vertical histogram of line image is employed to segment the printed Arabic text line into sub-words [20].…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Graph Modeling based Segmentation of Handwritten Arabic Text into Constituent Subwords

Ghaleb¹,

Nagabhushan²,

Pal³

2016

IJIGSP

View full text Add to dashboard Cite

Abstract-Segmentation of Arabic text is a major challenge that shall be addressed by any recognition system. The cursive nature of Arabic writing makes it necessary to handle the segmentation issue at various levels. Arabic text line can be viewed as a sequence of words which in turn can be viewed as a sequence of subwords. Sub-words have the frequently encountered intrinsic property of sharing the same vertical space which makes vertical projection based segmentation technique inefficient. In this paper, the task of segmenting handwritten Arabic text at sub-word level is taken up. The proposed algorithm is based on pulling away the connected components to overcome the impossibility of separating them by vertical projection based approach. Graph theoretic modeling is proposed to solve the problem of connected component extraction. In the sequel, these components are subjected to thorough analysis in order to obtain the constituent sub-words where a sub-word may consist of many components. The proposed algorithm was tested using variety of handwritten Arabic samples taken from different databases and the results obtained are encouraging.

show abstract

A fast and accurate contour-based method for writer-dependent offline handwritten Farsi/Arabic subwords recognition

Fouladi

Araabi

Kabir

2013

IJDAR

View full text Add to dashboard Cite

W-TSV: Weighted topological signature vector for lexicon reduction in handwritten Arabic documents

Cited by 18 publications

References 34 publications

A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: study case on Malay word recognition

A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: study case on Malay word recognition

Graph Modeling based Segmentation of Handwritten Arabic Text into Constituent Subwords

A fast and accurate contour-based method for writer-dependent offline handwritten Farsi/Arabic subwords recognition

Contact Info

Product

Resources

About