Home > Research > Publications & Outputs > Measuring and optimising performance of an offl...

Research

Links

Text available via DOI:

View graph of relations

Measuring and optimising performance of an offline text writer identification system in terms of dimensionality reduction techniques

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Measuring and optimising performance of an offline text writer identification system in terms of dimensionality reduction techniques. / Durou, Amal; Aref, Ibrahim; Elbendak, Mosa et al.
2017 Seventh International Conference on Emerging Security Technologies (EST). IEEE, 2017. (International Conference on Emerging Security Technologies (EST)).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Durou, A, Aref, I, Elbendak, M, Al-Maadeed, S & Bouridane, A 2017, Measuring and optimising performance of an offline text writer identification system in terms of dimensionality reduction techniques. in 2017 Seventh International Conference on Emerging Security Technologies (EST). International Conference on Emerging Security Technologies (EST), IEEE. https://doi.org/10.1109/EST.2017.8090393

APA

Durou, A., Aref, I., Elbendak, M., Al-Maadeed, S., & Bouridane, A. (2017). Measuring and optimising performance of an offline text writer identification system in terms of dimensionality reduction techniques. In 2017 Seventh International Conference on Emerging Security Technologies (EST) (International Conference on Emerging Security Technologies (EST)). IEEE. https://doi.org/10.1109/EST.2017.8090393

Vancouver

Durou A, Aref I, Elbendak M, Al-Maadeed S, Bouridane A. Measuring and optimising performance of an offline text writer identification system in terms of dimensionality reduction techniques. In 2017 Seventh International Conference on Emerging Security Technologies (EST). IEEE. 2017. (International Conference on Emerging Security Technologies (EST)). Epub 2017 Sept 6. doi: 10.1109/EST.2017.8090393

Author

Durou, Amal ; Aref, Ibrahim ; Elbendak, Mosa et al. / Measuring and optimising performance of an offline text writer identification system in terms of dimensionality reduction techniques. 2017 Seventh International Conference on Emerging Security Technologies (EST). IEEE, 2017. (International Conference on Emerging Security Technologies (EST)).

Bibtex

@inproceedings{7486377a40eb4695af519082cae49520,
title = "Measuring and optimising performance of an offline text writer identification system in terms of dimensionality reduction techniques",
abstract = "Usually, most of the data generated in real-world such as images, speech signals, or fMRI scans has a high dimensionality. Therefore, dimensionality reduction techniques can be used to reduce the number of variables in that data and then the system performance can be improved. Because the processing of the high dimensional data leads the increase of complexity both in execution time and memory usage. In the previous work, we developed an offline writer identification system using a combination of Oriented Basic Image features (OBI) and the concept of graphemes codebook. In order to measure and optimise the system performance, a variety of nonlinear dimensionality reduction algorithms such as Kernel Principal Component Analysis (KPCA), Isomap, Locally linear embedding (LLE), Hessian LLE and Laplacian Eigenmaps have been used. The performance has been evaluated based on IAM dataset for English handwriting and ICFHR 2012 dataset for Arabic handwriting. The results obtained indicated the system performance based KPCA was better than the other reduction techniques that have been used and investigated in this work.",
author = "Amal Durou and Ibrahim Aref and Mosa Elbendak and Sumaya Al-Maadeed and Ahmed Bouridane",
year = "2017",
month = nov,
day = "2",
doi = "10.1109/EST.2017.8090393",
language = "English",
isbn = "9781538640197",
series = "International Conference on Emerging Security Technologies (EST)",
publisher = "IEEE",
booktitle = "2017 Seventh International Conference on Emerging Security Technologies (EST)",

}

RIS

TY - GEN

T1 - Measuring and optimising performance of an offline text writer identification system in terms of dimensionality reduction techniques

AU - Durou, Amal

AU - Aref, Ibrahim

AU - Elbendak, Mosa

AU - Al-Maadeed, Sumaya

AU - Bouridane, Ahmed

PY - 2017/11/2

Y1 - 2017/11/2

N2 - Usually, most of the data generated in real-world such as images, speech signals, or fMRI scans has a high dimensionality. Therefore, dimensionality reduction techniques can be used to reduce the number of variables in that data and then the system performance can be improved. Because the processing of the high dimensional data leads the increase of complexity both in execution time and memory usage. In the previous work, we developed an offline writer identification system using a combination of Oriented Basic Image features (OBI) and the concept of graphemes codebook. In order to measure and optimise the system performance, a variety of nonlinear dimensionality reduction algorithms such as Kernel Principal Component Analysis (KPCA), Isomap, Locally linear embedding (LLE), Hessian LLE and Laplacian Eigenmaps have been used. The performance has been evaluated based on IAM dataset for English handwriting and ICFHR 2012 dataset for Arabic handwriting. The results obtained indicated the system performance based KPCA was better than the other reduction techniques that have been used and investigated in this work.

AB - Usually, most of the data generated in real-world such as images, speech signals, or fMRI scans has a high dimensionality. Therefore, dimensionality reduction techniques can be used to reduce the number of variables in that data and then the system performance can be improved. Because the processing of the high dimensional data leads the increase of complexity both in execution time and memory usage. In the previous work, we developed an offline writer identification system using a combination of Oriented Basic Image features (OBI) and the concept of graphemes codebook. In order to measure and optimise the system performance, a variety of nonlinear dimensionality reduction algorithms such as Kernel Principal Component Analysis (KPCA), Isomap, Locally linear embedding (LLE), Hessian LLE and Laplacian Eigenmaps have been used. The performance has been evaluated based on IAM dataset for English handwriting and ICFHR 2012 dataset for Arabic handwriting. The results obtained indicated the system performance based KPCA was better than the other reduction techniques that have been used and investigated in this work.

U2 - 10.1109/EST.2017.8090393

DO - 10.1109/EST.2017.8090393

M3 - Conference contribution/Paper

SN - 9781538640197

T3 - International Conference on Emerging Security Technologies (EST)

BT - 2017 Seventh International Conference on Emerging Security Technologies (EST)

PB - IEEE

ER -