2011 5th International Conference on Application of Information and Communication Technologies (AICT) 2011
DOI: 10.1109/icaict.2011.6110959
|View full text |Cite
|
Sign up to set email alerts
|

Arabic handwritten datasets for pattern recognition and machine learning

Abstract: Absract-This paper describes the efforts of SUST-ALT (Sudan University of Science and Technology-Arabic Language Technology group) research group towards building datasets for research in recognition of Arabic handwritten. The data sets contain: numerals datasets, isolated Arabic letters datasets, Arabic names datasets. Most of these datasets are off-line. The paper also describes some published results as well as future work.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2016
2016
2022
2022

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 6 publications
(3 citation statements)
references
References 3 publications
0
3
0
Order By: Relevance
“…The newly used SUST ALT (Sudan University of Science and Technology – Arabic Language Technology group) database includes several Arabic handwritten databases. The digits database and the isolated letters database (34 classes) are created from scratch, while the source of the names database (40 classes) is the SUST graduation certificate application forms [ 19 , 33 ]. Table 2 , Table 3 and Table 4 present some raw samples of the experiments on databases based on their types while covering digits, characters, and words from the Arabic handwritten databases, respectively.…”
Section: Experiments and Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…The newly used SUST ALT (Sudan University of Science and Technology – Arabic Language Technology group) database includes several Arabic handwritten databases. The digits database and the isolated letters database (34 classes) are created from scratch, while the source of the names database (40 classes) is the SUST graduation certificate application forms [ 19 , 33 ]. Table 2 , Table 3 and Table 4 present some raw samples of the experiments on databases based on their types while covering digits, characters, and words from the Arabic handwritten databases, respectively.…”
Section: Experiments and Discussionmentioning
confidence: 99%
“…Multilayer DNN derivatives, such as stacked auto-encoder (SAE), deep belief network (DBN), recurrent neural network (RNN), and convolutional neural networks (CNNs), have proven their high performance and accuracy [ 10 , 28 , 31 , 32 ]. The CNN has shown that it outperforms state-of-the-art approaches [ 33 ] in various fields, including face recognition, object recognition, and image classification [ 22 , 23 , 34 , 35 , 36 ]. The CNN architecture is a multi-layer feed-forward neural network that adopts the back-propagation algorithm to learn and automatically extract features from high-dimensional and complex data such as images [ 9 , 37 , 38 , 39 , 40 ].…”
Section: Introductionmentioning
confidence: 99%
“…A. Data Set: SUST ALT (Sudan University of Science and Technology-Arabic Language Technology group) has built many datasets to be used in studying, investigating, training, and testing Arabic recognizers [7,8]. Isolated Arabic letters is one of these data set.…”
Section: Methodsmentioning
confidence: 99%