A Comparative Study of Machine Learning Approaches for Handwriter Identification

Durou, Amal; Al-Maadeed, Somaya; Aref, Ibrahim; Bouridane, Ahmed; Elbendak, Mosa

doi:10.1109/icgs3.2019.8688032

Cited by 4 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the contrary, our work mainly focuses on getting a scientific explanation by comparative study without any additional method or specific approach to the handwriting writer identification problem. We prove that the best suitable DL in the convergence gap area between training and validation accuracy, which is ExceptionNet without the additional methods mentioned above, has almost reached state-of-the-art accuracy produced by previous studies in IAM dataset [16], [17], [20], [22] with the highest accuracy 99.5% using ResNet with a difference of 1.2% with our accuracy of 98.3% and CVL dataset [9], [10], [22] which is identical 98.3%. This accuracy gap of 1.2% in the IAM dataset is because we have yet to work out of scope focus on this paper, the overfitting problems.…”

Section: B Performance Comparison With Previous Researchmentioning

confidence: 52%

“…Most researchers from previous studies mainly focusing developing additional methods or specific approaches, e.g. [7][8][9][10][11][12][13][14][15][16][17][18][19] with arbitrary DL selected to get the best accuracy in writer identification with TopN, SoftN, or HardN evaluation metrics performance. On the contrary, our work mainly focuses on getting a scientific explanation by comparative study without any additional method or specific approach to the handwriting writer identification problem.…”

Section: B Performance Comparison With Previous Researchmentioning

confidence: 99%

“…[16] utilized CNN with four convolutional layers for text-independent author identification on JEITA-HP offline handwritten Japanese characters, firemaker dataset, and IAM database as an end-toend network. Durou et al [17] conducted a comparison study for handwriter identification using modified AlexNet architecture with SVM and KNN classification on IAM and ICFHR 2012 Arabic handwriting dataset, which resulted in the DL method showing better results than the conventional method. Similarly, Helal et al [18] experimented CNN DL with an addition dissimilarity approach with an SVM classifier using CVL and BFL databases.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

End-To-End Evaluation of Deep Learning Architectures for Off-Line Handwriting Writer Identification: A Comparative Study

Suteddy

Agustini

Adiwilaga

et al. 2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Identifying writers using their handwriting is particularly challenging for a machine, given that a person’s writing can serve as their distinguishing characteristic. The process of identification using handcrafted features has shown promising results, but the intra-class variability between authors still needs further development. Almost all computer vision-related tasks use Deep learning (DL) nowadays, and as a result, researchers are developing many DL architectures with their respective methods. In addition, feature extraction, usually accomplished using handcrafted algorithms, can now be automatically conducted using convolutional neural networks. With the various developments of the DL method, it is necessary to evaluate the suitable DL for the problem we are aiming at, namely the classification of writer identification. This comparative study evaluated several DL architectures such as VGG16, ResNet50, MobileNet, Xception, and EfficientNet end-to-end to examine their advantages to offline handwriting for writer identification problems with IAM and CVL databases. Each architecture compared its respective process to the training and validation metrics accuracy, demonstrating that ResNet50 DL had the highest train accuracy of 98.86%. However, Xception DL performed slightly better due to the convergence gap for validation accuracy compared to all the other architectures, which were 21.79% and 15.12% for IAM and CVL. Also, the smallest gap of convergence between training and validation accuracy for the IAM and CVL datasets were 19.13% and 16.49%, respectively. The results of these findings serve as the basis for DL architecture selection and open up overfitting problems for future work.

show abstract

Section: B Performance Comparison With Previous Researchmentioning

confidence: 52%

Section: B Performance Comparison With Previous Researchmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

End-To-End Evaluation of Deep Learning Architectures for Off-Line Handwriting Writer Identification: A Comparative Study

Suteddy

Agustini

Adiwilaga

et al. 2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

show abstract

“…An interesting work has also been presented in Durou et al (2019) where a manual feature extraction based approach is compared with the automated feature extraction method. In the first category, SURF and SIFT methods were utilized during the feature extraction step and then the SVM and k-NN classifiers were used during writers classification.…”

Section: Related Workmentioning

confidence: 99%

Writer verification of partially damaged handwritten Arabic documents based on individual character shapes

Khan

Mohammad

Brahim

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

Author verification of handwritten text is required in several application domains and has drawn a lot of attention within the research community due to its importance. Though, several approaches have been proposed for the text-independent writer verification of handwritten text, none of these have addressed the problem domain where author verification is sought based on partially-damaged handwritten documents (e.g., during forensic analysis). In this paper, we propose an approach for offline text-independent writer verification of handwritten Arabic text based on individual character shapes (within the Arabic alphabet). The proposed approach enables writer verification for partially damaged documents where certain handwritten characters can still be extracted from the damaged document. We also provide a mechanism to identify which Arabic characters are more effective during the writer verification process. We have collected a new dataset, Arabic Handwritten Alphabet, Words and Paragraphs Per User (AHAWP), for this purpose in a classroom setting with 82 different users. The dataset consists of 53,199 user-written isolated Arabic characters, 8,144 Arabic words, 10,780 characters extracted from these words. Convolutional neural network (CNN) based models are developed for verification of writers based on individual characters with an accuracy of 94% for isolated character shapes and 90% for extracted character shapes. Our proposed approach provided up to 95% writer verification accuracy for partially damaged documents.

show abstract

Document Filter for Writer Identification

Pignelli

Oliveira

Britto

et al. 2022

Communications in Computer and Information Science

View full text Add to dashboard Cite

A Comparative Study of Machine Learning Approaches for Handwriter Identification

Cited by 4 publications

References 19 publications

End-To-End Evaluation of Deep Learning Architectures for Off-Line Handwriting Writer Identification: A Comparative Study

End-To-End Evaluation of Deep Learning Architectures for Off-Line Handwriting Writer Identification: A Comparative Study

Writer verification of partially damaged handwritten Arabic documents based on individual character shapes

Document Filter for Writer Identification

Contact Info

Product

Resources

About