Spectral minutiae for vein pattern recognition

Hartung, Daniel; Olsen, Martin Aastrup; Xu, Haiyun; Busch, Christoph

doi:10.1109/ijcb.2011.6117549

Cited by 31 publications

(23 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work different level of skeleton fusion was used followed by chain code. In [19] spectral minutia based feature extraction was used to represent the wrist vein pattern after preprocessing the vein images. An approach to extract the vein minutiae and to transform them into a fixed-length, translation and scale invariant representation where rotations can be easily compensated is presented in [21].…”

Section: Introductionmentioning

confidence: 99%

A new wrist vein biometric system

Das

Pal

Ferrer

et al. 2014

2014 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management (CIBIM)

View full text Add to dashboard Cite

In this piece of work a wrist vein pattern recognition and verification system is proposed. Here the wrist vein images from the PUT database were used, which were acquired in visible spectrum. The vein image only highlights the vein pattern area so, segmentation was not required. Since the wrist's veins are not prominent, image enhancement was performed. An Adaptive Histogram Equalization and Discrete Meyer Wavelet were used to enhance the vessel patterns. For feature extraction, the vein pattern is characterized with Dense Local Binary Pattern (D-LBP). D-LBP patch descriptors of each training image are used to form a bag of features, which was used to produce the training model. Support Vector Machines (SVMs) were used for classification. An encouraging Equal Error Rate (EER) of 0.79% was achieved in our experiments.

show abstract

Section: Introductionmentioning

confidence: 99%

A new wrist vein biometric system

Das

Pal

Ferrer

et al. 2014

2014 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management (CIBIM)

View full text Add to dashboard Cite

show abstract

“…If the performance results of the V-MCC algorithm are compared to Spectral Minutiae (SM) [6,7] on the same data, the following observations can be made: SM performs better on SNIR (0.41% vs. 1.45% EER) and SFIR-GT data (0.06% vs. 1.88% EER); V-MCC outperforms SM significantly on UC3M data (4.37% vs. 0.31% EER), V-MCC even outperforms the state-of-the-art similarity mixed-matching algorithm (SMM) [3]. Considering the minutiae statistics from Table 3, the V-MCC seems to be able to compensate much better for spurious minutiae that are obviously present in the UC3M dataset.…”

Section: Discussionmentioning

confidence: 99%

“…The minutiae points of all samples of the specific database are extracted according to the preprocessing introduced in [6]. As a first step, the vein minutiae information is encoded as MCC templates using the standard parameters as introduced in [2].…”

Section: Training Protocolmentioning

confidence: 99%

“…The spectral minutiae proposed in [15] is such a representation method that offers a fixed structure of the features and is invariant to translation and scaling of the input, rotations can be easily compensated. The originally proposed parameter set could be utilized for vein data [6,7]. However, for the investigated datasets representing different vein modalities, the recognition performance was deviating strongly.…”

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

Vein minutia cylinder-codes (V-MCC)

Hartung

Tistarelli

Busch

2013

2013 International Conference on Biometrics (ICB)

Self Cite

View full text Add to dashboard Cite

Vein recognition has been extensively studied in the past. The topology of the vein patterns allows to adopt simple representations, based on edges and their endings, which are quite similar to the fingerprint minutiae. In this paper, the Minutia Cylinder-Codes (MCC), developed for the comparison of fingerprint minutiae, are adapted to characterize vein minutiae. The algorithm adaptation requires to understand the vein topology and how to consequently define the parameter sets. An optimization problem is defined and solved using a genetic algorithm (GA) approach. The experimental results prove the applicability of MCC on three extended vein data sets of wrist and palm dorsal. The performance of the reference parameter set is improved and can compete with other state-of-the-art algorithms for vein verification.

show abstract

“…We compared the performance to the evaluation results of spectral minutiae (SML and SMLFR) as proposed in [12], Similarity-based Mix-Matching (SMM) [4] and the performance of chain code comparison on single references and fused skeletons. In all experiments using fused skeletons, the fused skeleton served as the reference image and a skeleton extracted from one vein image was used as the probe image.…”

Section: Feature Extraction Evaluationmentioning

confidence: 99%