Publication: Authentication of genuine and fake certificates using machine learning
| dc.contributor.author | Amran, Asyiq Syahm | |
| dc.date.accessioned | 2026-08-19T06:59:31Z | |
| dc.date.available | 2026-08-19T06:59:31Z | |
| dc.date.issued | 2026-02 | |
| dc.description.abstract | The proliferation of fake academic certificates in Malaysia has poses a crucial threat to the integrity of higher education and the credibility of the national workforce. This study was aimed to differentiate genuine and fake academic certificates by analysing their visual textural features through machine learning-based algorithms. In this study, the original physical certificates were digitalised at four scanning resolutions (100 to 400 DPI) and systematically creating 180 fake samples using nine distinct alteration methods using Adobe® Photoshop® software. Textural information was then extracted using the Gray-Level Co-occurrence Matrix (GLCM) while statistical tests were conducted to investigate the influence of the four scanning resolution and effects of different three conversion methods. The results demonstrated that scanning resolution and conversion methods possessed influence in generating the scanned certificates. Both random forest (RF) and support vector machine (SVM) models were effective for binary classification. However, in the multiclass classification of specific forgery types, the RF model outperformed the SVM. Overall, the research underscored the critical role of scanning resolution in shaping textural feature quality and validated the effectiveness of machine learning algorithms in certificate authentication. By demonstrating the feasibility of automated and scalable detection systems, this study contributed to safeguarding institutional integrity and protecting the value of educational qualifications, offering a practical pathway toward strengthening trust in Malaysia’s academic and professional landscape. | |
| dc.identifier.uri | https://erepo.usm.my/handle/123456789/24865 | |
| dc.language.iso | en | |
| dc.subject | Certificate authentication | |
| dc.subject | machine learning | |
| dc.title | Authentication of genuine and fake certificates using machine learning | |
| dc.type | Resource Types::text::thesis::bachelor thesis | |
| dspace.entity.type | Publication | |
| oairecerif.author.affiliation | Universiti Sains Malaysia |