Proceedings ArticleDOI
A fingerprint matching method using DCT features
S. Tachaphetpiboon,Thumrongrat Amornraksa +1 more
- Vol. 1, pp 461-464
TLDR
With this proposed method, both higher recognition rate and lower complexity can be achieved at the same time.Abstract:
This paper proposes an extraction method of DCT features for fingerprint matching. In the features extraction process, a fingerprint image is quartered and transformed by the DCT. The standard deviation of the DCT coefficients in predefined areas is then calculated and used for fingerprint matching. The recognition rate of the proposed method is evaluated by the k-NN classifier. The results obtained are finally compared to the existing method based on the wavelet features. The processing time required in both features extraction and matching processes between two approaches are also compared. With our proposed method, both higher recognition rate and lower complexity can be achieved at the same time.read more
Citations
More filters
Journal ArticleDOI
Weighted quasi-arithmetic mean based score level fusion for multi-biometric systems
TL;DR: A novel scheme for score-level fusion based on weighted quasi-arithmetic mean (WQAM) has been proposed, which outperforms the previously proposed score fusion rules based on transformation, classification and density estimation methods.
Proceedings ArticleDOI
Fingerprint matching using transform features
M. P. Dale,Madhuri Joshi +1 more
TL;DR: The technique described here obviates the need for extracting minutiae points to match fingerprint images and it is observed that DCT and DFT gives better result as compared DWT.
Proceedings ArticleDOI
DCT feature based fingerprint recognition
TL;DR: DCT based feature vector for fingerprint representation and matching is proposed by dividing the transformed image into various blocks, standard deviation is calculated for each block and such 96 standard deviations will form the feature vector used in matching stage.
Book ChapterDOI
Fingerprint Identification — Ideas, Influences, and Trends of New Age
Sangita Bharkad,Manesh Kokare +1 more
TL;DR: A survey of current fingerprint matching methods and technical achievement in this area includes a large number of papers covering the research aspects of system design and applications of fingerprint matching, image feature representation and extraction.
Proceedings ArticleDOI
Efficient Fingerprint Matching Technique Using Wavelet Based Features
TL;DR: This paper details the work of an efficient fingerprint matching technique via the use of wavelet based features which has provided success rate up to 93.75% on standard database and can recognize one fingerprint in less then 0.
References
More filters
Journal ArticleDOI
Fingerprint feature extraction using Gabor filters
Chih-Jen Lee,Sheng-De Wang +1 more
TL;DR: A Gabor filter-based method for directly extracting fingerprint features from grey-level images without pre-processing is introduced and shows that the recognition rate of the k-nearest neighbour classifier using the proposed Gabor Filter-based features is 97.2%.
Proceedings ArticleDOI
Fingerprint recognition using wavelet features
TL;DR: The very high recognition rates achieved show that the proposed method may constitutes an efficient solution for a small-scale fingerprint recognition system.
Journal ArticleDOI
Wavelet domain features for fingerprint recognition
TL;DR: A fingerprint recognition approach based on features extracted from the wavelet transform of the discrete image is presented and it is shown that this method requires lower computational effort than most of the fingerprint recognition methods proposed to date.
Proceedings ArticleDOI
Minutiae extraction scheme for fingerprint recognition systems
TL;DR: Conclusions in terms of Goodness Index (GI), which compares the results obtained by automatic minutiae extraction with manually extracted ones, are provided in order to test the global performance of this approach.
Proceedings ArticleDOI
A Gabor filter-based approach to fingerprint recognition
Chih-Jen Lee,Sheng-De Wang +1 more
TL;DR: Experimental results show that the recognition rate of the k-nearest neighbor classifier using the proposed features is 97.2% for a small-scale fingerprint database, and thus that the proposed method is an efficient and reliable approach.