Auto Machine Learning-Based Approach for Source Printer Identification

Vo, Phu-Qui; Dang, Nhan Tam; Nguyen, Quang Phu; Mai, An; Nguyen, Loan T. T.; Nguyen, Quoc-Thông; Nguyen, Ngoc Thanh

doi:10.1007/978-981-19-8234-7_52

Cited by 1 publication

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In comparing the results across the various models utilized in this research, we observe that the accuracy achieved is relatively high. The percentages provided range from 95.56% to 100% in comparison with the range from 66% to 80% in our previous study (Vo et al, 2022). This shows the effectiveness of the methodologies applied and the feasibility of using the deep learning approach for microscopic printer identification.…”

Section: Training Procedures and Evaluation Metricssupporting

confidence: 46%

See 1 more Smart Citation

Analysis of printed document identification based on Deep Learning

Nguyen,

Mai

2023

CTU J. of Inn. & Sus. Dev.

View full text Add to dashboard Cite

In this study, we investigate the effectiveness of ResNet, a deep neural network architecture, for a deep learning approach to address the problem of printed document identification. ResNet is known for its ability to handle the vanishing gradient problem and learn highly representative features. Multiple variations of ResNet have been applied, including ResNet50, ResNet101, and ResNet152, which provide the backbone architecture of our classification model and are trained on a comprehensive dataset of microscopic printed images containing some microscopic printing patterns from various source printers. We also incorporate Mix-up augmentation, a technique that generates virtual training samples by interpolating pairs of images and labels, to further enhance the performance and generalization capability of the model. The experimental results showed that ResNet101 and ResNet152 variants outperformed in accurately distinguishing printer sources based on microscopic printed patterns. We developed a mobile app to test the feasibility of our findings in practice. In conclusion, this study aims to lay the groundwork for creating a sufficiently pre-trained model with accurate performance of identification that can be deployed on mobile devices to detect the printed sources of documents.

show abstract

Section: Training Procedures and Evaluation Metricssupporting

confidence: 46%

“…In this study, we examined the same dataset with authors from , , and (Vo et al, 2022) which contain microscopic images of eight distinguished patterns printed using three different printing technologies on two types of papers. This dataset was achieved with numerous hours of labor following these steps:…”

Section: Datasetmentioning

confidence: 99%

Analysis of printed document identification based on Deep Learning

Nguyen,

Mai

2023

CTU J. of Inn. & Sus. Dev.

View full text Add to dashboard Cite

show abstract

Auto Machine Learning-Based Approach for Source Printer Identification

Cited by 1 publication

References 16 publications

Analysis of printed document identification based on Deep Learning

Analysis of printed document identification based on Deep Learning

Contact Info

Product

Resources

About