Openly accessible

Automatic visual features for writer identification: a deep learning approach

Rehman, Arshia, Naz, Saeeda, Razzak, Muhammad Imran and Hameed, Ibrahim A. 2019, Automatic visual features for writer identification: a deep learning approach, IEEE access, vol. 7, pp. 17149-17157, doi: 10.1109/ACCESS.2018.2890810.

Attached Files
Name Description MIMEType Size Downloads

Title Automatic visual features for writer identification: a deep learning approach
Author(s) Rehman, Arshia
Naz, Saeeda
Razzak, Muhammad ImranORCID iD for Razzak, Muhammad Imran orcid.org/0000-0002-3930-6600
Hameed, Ibrahim A.
Journal name IEEE access
Volume number 7
Start page 17149
End page 17157
Total pages 9
Publisher IEEE
Place of publication Piscataway, N.J.
Publication date 2019
ISSN 2169-3536
2169-3536
Summary © 2013 IEEE. Identification of a person from his writing is one of the challenging problems; however, it is not new. No one can repudiate its applications in a number of domains, such as forensic analysis, historical documents, and ancient manuscripts. Deep learning-based approaches have proved as the best feature extractors from massive amounts of heterogeneous data and provide promising and surprising predictions of patterns as compared with traditional approaches. We apply a deep transfer convolutional neural network (CNN) to identify a writer using handwriting text line images in English and Arabic languages. We evaluate different freeze layers of CNN (Conv3, Conv4, Conv5, Fc6, Fc7, and fusion of Fc6 and Fc7) affecting the identification rate of the writer. In this paper, transfer learning is applied as a pioneer study using ImageNet (base data-set) and QUWI data-set (target data-set). To decrease the chance of over-fitting, data augmentation techniques are applied like contours, negatives, and sharpness using text-line images of target data-set. The sliding window approach is used to make patches as an input unit to the CNN model. The AlexNet architecture is employed to extract discriminating visual features from multiple representations of image patches generated by enhanced pre-processing techniques. The extracted features from patches are then fed to a support vector machine classifier. We realized the highest accuracy using freeze Conv5 layer up to 92.78% on English, 92.20% on Arabic, and 88.11% on the combination of Arabic and English, respectively.
Language eng
DOI 10.1109/ACCESS.2018.2890810
Indigenous content off
HERDC Research category C1.1 Refereed article in a scholarly journal
Free to Read? Yes
Persistent URL http://hdl.handle.net/10536/DRO/DU:30132544

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 6 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 23 Abstract Views, 2 File Downloads  -  Detailed Statistics
Created: Tue, 26 Nov 2019, 08:38:18 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.