Abstract/Description
This paper presents a fingerprint matching scheme that utilizes a ridge patterns to match fingerprint images. The proposed scheme uses a set of 16 Gabor filters where spatial frequencies correspond to the average inter-ridge spacing in fingerprints. It is used to capture the ridge strength at equally spaced orientations. A circular tessellation of filtered image is then used to construct the ridge feature map. This ridge feature map contains both global and local details in a fingerprint as a compact fixed length feature vector. The fingerprint matching is based on the Euclidean distance between two corresponding feature vectors. The genuine accept rate of the Ridge Pattern based matcher is observed to be about 5% to 8% higher than that of minutiae-based matcher at low false accept rates. Fingerprint feature extraction and matching takes nearly 7 seconds on a normal Pentium IV machine.
Keywords
Gabor filters, Feature vector, Texture, Fingerprints, Matching, Verification, Core point
Location
Crystal Ball Room A, Hotel Pearl Continental, Karachi, Pakistan
Session Theme
Poster Session A: Artificial Intelligence [AI-1]
Session Type
Poster Session
Session Chair
Dr. Arshad B. Siddiqui
Start Date
28-8-2005 12:05 PM
End Date
28-8-2005 12:25 PM
Recommended Citation
Munir, M. U., & Javed, D. Y. (2005). Poster Session A: Fingerprint Matching using Ridge Patterns. International Conference on Information and Communication Technologies. Retrieved from https://ir.iba.edu.pk/icict/2005/2005/12
Poster Session A: Fingerprint Matching using Ridge Patterns
Crystal Ball Room A, Hotel Pearl Continental, Karachi, Pakistan
This paper presents a fingerprint matching scheme that utilizes a ridge patterns to match fingerprint images. The proposed scheme uses a set of 16 Gabor filters where spatial frequencies correspond to the average inter-ridge spacing in fingerprints. It is used to capture the ridge strength at equally spaced orientations. A circular tessellation of filtered image is then used to construct the ridge feature map. This ridge feature map contains both global and local details in a fingerprint as a compact fixed length feature vector. The fingerprint matching is based on the Euclidean distance between two corresponding feature vectors. The genuine accept rate of the Ridge Pattern based matcher is observed to be about 5% to 8% higher than that of minutiae-based matcher at low false accept rates. Fingerprint feature extraction and matching takes nearly 7 seconds on a normal Pentium IV machine.