Personal authentication through dorsal hand vein patterns

Palm vein recognition based on multi-sampling and feature-level fusion

“…However, feature extraction and comparison are difficult when the geometry features are not obvious [28]. The statistics-based method extracts global features, such as invariant moment features [18] and feature space [29], but some local features are lost in the statistics-based method.…”

Combining local and global features based on the eigenspace for vein recognition

“…To evaluate the effectiveness of the proposed method for dorsal hand vein recognition, we used the Near-Infrared (NIR) dorsal hand vein image database [11]. The database includes 4280 dorsal hand vein images from 214 different volunteers with twenty images captured from each class.…”

“…Finally, minimum distance classifier (MDC) is used for feature matching and classification. Experimental results on Hsu's [11] databases show that the proposed approach is robust.…”

“…Crisan et al [10] used morphological feature extractor and statistical feature extractor for hand vein recognition. Yuksel et al [11] extracted the features from images of hands using a geometric method and two appearance-based methods. Hsu et al [12] has successfully used the modified 2-directional 2-dimensional principal component analysis ((2D) 2 PCA) method to obtain eigenvein which is a low dimensional representation of vein pattern features.…”

“…Many verification technologies using biometric features of hand vein were developed over the past decades [3][4][5][6][7][8][9][10][11][12]. Cross and Smith [3] have detailed the usage of near IR imaging for the extraction of hand vein patterns and have demonstrated the two-fold matching of medial axis representation, following the vein skeleton extraction.…”