Fingerprint Classification based on Simplified Rule set and Singular Points with an Image Enhancement Scheme
Sibiyakhan M1, Sumithra M D2
1Sibiyakhan M, M.Tech Scholar, Department of Computer Science and Engineering, LBS Institute of Technology for Women, Thiruvananthapuram (Kerala), India.
2Sumithra M D, Assistant Professor, Department of Computer Science and Engineering, LBS institute of Technology for Women, Thiruvananthapuram (Kerala), India.
Manuscript received on 13 August 2016 | Revised Manuscript received on 20 August 2016 | Manuscript Published on 30 August 2016 | PP: 168-171 | Volume-5 Issue-6, August 2016 | Retrieval Number: F4708085616/16©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: A rule-based technique using simplified rules is proposed to overcome the challenges faced by previous fingerprint classification techniques. Two features, namely directional patterns and singular points (SPs), are combined to categorize four fingerprint classes: namely Whorl (W); Loop (L); Arch (A); and Unclassifiable (U). The use of directional patterns has recently received more attention in fingerprint classification. It provides a global representation of a fingerprint, by dividing it into homogeneous orientation partitions. With this technique, We can improve the accuracy of the classification by integrating an image enhancement scheme. In addition, incomplete fingerprints are often not accounted for. The proposed technique achieves an accuracy of 93.33% on the FVC 2002 DB1.
Keywords: Singular Point (SP), Core Point, Delta Point, Segmentation, Preprocessing.
Scope of the Article: Classification