Fingerprint images segmentation using two stages coarse to fine discrimination technique


Ong, Teng Sian and Sek, Y. W. and Ngo, David Chek Ling and Teoh, Andrew Beng Jin (2003) Fingerprint images segmentation using two stages coarse to fine discrimination technique. In: Australasian Joint Conference on Artificial Intelligence.

Full text not available from this repository.


Segmentation of fingerprint image is necessary to reduce the size of the input data, eliminating undesired background, which is the noisy and smudged area in favor of the central part of the fingerprint. In this paper, an algorithm for the segmentation which uses two stages coarse to fine approach is presented. The coarse segmentation will be performed at first using the orientation certainty values that derived from the blockwise directional field of the fingerprint image. The coarse segmented image will be carry on to the second stage which consist Fourier based enhancement and adaptive thresholding. Orientation certainty values of the resultant binarized image are calculated once again to perform the fine segmentation. Finally, binary image processing is applied as postprocessing to further reduce the segmentation error. Visual inspection shows that the proposed method produce accurate segmentations result. The algorithm is also evaluated by counting the number of false and missed detected center points and compare with the fingerprint image which have no segmentation and with the proposed method without postprocessing. Experiments show that the proposed segmentation method perform well than others.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Gabor Filter, Binary Mask, Fingerprint Image, Segmentation Error, Adaptive Thresholding
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Rosnani Abd Wahab
Date Deposited: 24 Aug 2011 01:06
Last Modified: 02 Jan 2023 10:40


Downloads per month over past year

View ItemEdit (login required)