Publication: Development of fingerprint system
| datacite.subject.fos | oecd::Engineering and technology::Electrical engineering, Electronic engineering, Information engineering::Electrical and electronic engineering | |
| dc.contributor.author | Syuhaeil Adib bin Sabri | |
| dc.date.accessioned | 2025-05-19T03:39:15Z | |
| dc.date.available | 2025-05-19T03:39:15Z | |
| dc.date.issued | 2024-07 | |
| dc.description.abstract | This thesis presents a comprehensive study on the development of fingerprint system which aimed to enhance security and streamlining identification process. The main objectives of this study are to design a fingerprint recognition system that efficiently applies the SIFT algorithm for feature extraction, to develop an intuitive graphical user interface (GUI) that enables effortless system interaction, and to improve fingerprint image quality through the application of sophisticated preprocessing techniques. The method uses frequency filtering, orientation estimation, and ridge segmentation three sophisticated image processing techniques to enhance the quality of fingerprint images. The Scale-Invariant Feature Transform (SIFT) technique is used for feature extraction. It finds and defines key points that are necessary for precise matching. In order to ensure accurate and reliable feature matching, the system uses the FLANN (Fast Library for Approximate Nearest Neighbors) algorithm in conjunction with RANSAC (Random Sample Consensus) throughout the matching process. The system's performance is evaluated using metrics such as False Match Rate (FMR), False Non-Match Rate (FNMR), and Equal Error Rate (EER), calculated across a comprehensive dataset to ensure reliability and robustness. Peak Signal-to-Noise Ratio (PSNR), a quantitative indicator of the quality of the enhancement, is used to evaluate the efficacy of the image processing procedures. Furthermore, fingerprint enrollment and identification are made easier by the intuitive graphical interface, which also offers visible feedback on the improvement process and features extracted. This interface makes the system accessible to non-experts and suitable for various security and identification applications. The success of the proposed method was proven by extensive experimental findings, which showed great accuracy and effectiveness through rigorous testing and analysis. | |
| dc.identifier.uri | https://erepo.usm.my/handle/123456789/21701 | |
| dc.language.iso | en | |
| dc.title | Development of fingerprint system | |
| dc.type | Resource Types::text::report::technical report | |
| dspace.entity.type | Publication | |
| oairecerif.author.affiliation | Universiti Sains Malaysia |