Fingerprint Preselection Using Eigenfeatures for a Large-Size Database

Kamei, Toshio

doi:10.1007/0-387-21685-5_13

Cited by 3 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, one can develop different mechanisms to calculate the distance between two feature vectors [29], [30] or apply different fingerprint retrieval strategies [20]. In this section, a new feature based on the FOMFE is introduced to enhance the performance of continuous classification and fingerprint indexing.…”

Section: Application To Fingerprint Indexingmentioning

confidence: 99%

See 1 more Smart Citation

A Fingerprint Orientation Model Based on 2D Fourier Expansion (FOMFE) and Its Application to Singular-Point Detection and Fingerprint Indexing

Wang

Phillips

2007

IEEE Trans. Pattern Anal. Mach. Intell.

263

167

View full text Add to dashboard Cite

Abstract-In this paper, we have proposed a fingerprint orientation model based on 2D Fourier expansions (FOMFE) in the phase plane. The FOMFE does not require prior knowledge of singular points (SPs). It is able to describe the overall ridge topology seamlessly, including the SP regions, even for noisy fingerprints. Our statistical experiments on a public database show that the proposed FOMFE can significantly improve the accuracy of fingerprint feature extraction and thus that of fingerprint matching. Moreover, the FOMFE has a low-computational cost and can work very efficiently on large fingerprint databases. The FOMFE provides a comprehensive description for orientation features, which has enabled its beneficial use in feature-related applications such as fingerprint indexing. Unlike most indexing schemes using raw orientation data, we exploit FOMFE model coefficients to generate the feature vector. Our indexing experiments show remarkable results using different fingerprint databases.

show abstract

Section: Application To Fingerprint Indexingmentioning

confidence: 99%

“…However, the resulting feature vector will have too many elements and is neither computationally efficient nor practical for most numerical classifiers. Therefore, a dimensionality reduction technique, such as the KarhunenLoève (KL) transform [31], is often applied to the OF [29], [32].…”

Section: Fingerprint Features For Indexingmentioning

confidence: 99%

A Fingerprint Orientation Model Based on 2D Fourier Expansion (FOMFE) and Its Application to Singular-Point Detection and Fingerprint Indexing

Wang

Phillips

2007

IEEE Trans. Pattern Anal. Mach. Intell.

263

167

View full text Add to dashboard Cite

show abstract

“…Instead of the orientation angle , some approaches [4], [14], [15] employ the unit orientation vector as the classification feature. While this representation is necessary to facilitate some feature transform and weighting, it doubles the size of the feature vector.…”

Section: B Orientation Feature Vector Constructionmentioning

confidence: 99%

“…where (8) Some approaches [4], [14], [15] employ the unit orientation vector representation. From the trigonometry, we can easily have (9) Obviously, if the Euclidean distance is applied, this unit vector representation that doubles the feature vector size maps in (6) to , which produces very similar distance to that of angle .…”

Section: Distance Measurementioning

confidence: 99%

“…Some approaches [4], [5], [14], [15] exploit the Karhunen-Loeve (KL) transformation (principle component analysis) or multispace KL to project the higher dimensional orientation feature vector onto a lower dimensional one. In the practical applications, feature vectors of different fingerprints may have quite different valid and invalid elements due to the translation, rotation, and unfavorable reference point locations.…”

Section: B Orientation Feature Vector Constructionmentioning

confidence: 99%

See 1 more Smart Citation

Fingerprint Retrieval for Identification

Jiang

Liu

Kot

2006

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Abstract-This paper presents a front-end filtering algorithm for fingerprint identification, which uses orientation field and dominant ridge distance as retrieval features. We propose a new distance measure that better quantifies the similarity evaluation between two orientation fields than the conventional Euclidean and Manhattan distance measures. Furthermore, fingerprints in the data base are clustered to facilitate a fast retrieval process that avoids exhaustive comparisons of an input fingerprint with all fingerprints in the data base. This makes the proposed approach applicable to large databases. Experimental results on the National Institute of Standards and Technology data base-4 show consistent better retrieval performance of the proposed approach compared to other continuous and exclusive fingerprint classification methods as well as minutia-based indexing schemes.

show abstract