This work aims to study the procedures of fingerprint identification system and to present some efficient algorithms for pre-processing and minutiae extraction. Most pre-processing steps consist of normalization, segmentation and orientation estimation, and background which focus on decreasing the variance of fingerprints, separating fore and background areas and tracking the direction of ridge lines, respectively. Minutiae extractionis typically divided into two approaches: binarization based method and directgray scale extraction. However, we put emphasis on binarization based method in thisresearch since it is more commonly used method in research papers. The results of simulationbased on a set of fingerprints downloaded from FVC 2006 database showed thatalgorithms we used are accurate and reliable.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:lnu-64819 |
| Date | January 2017 |
| Creators | Cao, Letian, Wang, Yazhou |
| Publisher | Linnéuniversitetet, Institutionen för fysik och elektroteknik (IFE), Linnéuniversitetet, Institutionen för fysik och elektroteknik (IFE), Linnaeus University, Linnaeus University |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0018 seconds