A Novel Palmprint Feature Processing Method Based on Skeleton Image

Abstract

This paper proposes a series of novel palmprint feature processing approaches based on the skeleton image. The skeleton images could be obtained from different kinds of input images and image processing approaches. This paper extracts both of the basic geometry attributes and additional structure information from the skeleton images. It extracts both of the palmprint minutiae feature and the local ridge feature, builds the relationship among the feature, and constructs the raw and rough feature set. For obtaining the final feature set, deleting the spurious feature while retaining the true feature as many as possible, the feature postprocessing approach proposed by this paper purifies the rough feature set based on the statistical and structural information, combing the information of the minutiae attribute, structural relationship in the minutiae subsets, the local ridge and the local region. We use and improve the point pattern matching approach in our previous work. It is a multi-phases minutiae matching based on both of the local structure and global feature. The experimental results reveal that the proposed feature processing approaches are effective and efficient for the practical requirement.

Combination a Skeleton Filter and Reduction Dimension of Kernel PCA Based on Palmprint Recognition

“…Filter skeleton has been previously used by Lin in his research to obtain all lines minutiae in palm [14]. The result is an ability of skeleton filter to improve the appearance of images, thus improving system performance and upgrade the point pattern matching approach.…”

Fast and efficient minutia‐based palmprint matching

“…(1) RP restriction: Statistical observations show that most regions, those with no distortion or creases, in a palmprint or fingerprint image, have an RP of 7 < RP < 13. It needs to be emphasised that this interval, RP ∈ [7,13], is true for images with 500 dpi. Generally, RP < 6 belongs to blocks with creases or background blocks, and RP > 14 is for background or the distorted regions of palmprints.…”

“…In the matching stage, the similarity between two palmprints is calculated by means of a weighted sum of minutiae and orientation field matching scores. Li describes a palmprint recognition algorithm in which minutiae are extracted and compared by means of a local and global matching [13]. In [9], a multi‐feature‐based palmprint recognition system is suggested.…”

3D minutiae extraction in 3D fingerprint scans.

“…Let t max and tmin be the corresponding principal directions which are the associated tangent directions of S at P. e max and emin denote the derivatives of the principal curvature along their corresponding curvature directions: (42) The point at which the principal curvatures are equal to each other (k max = k min ) is called umbilic. e max and emin are not defined at umbilic points, because the principal directions are undefined there.…”

“…Many papers use the aforementioned method for extracting minutiae from the skeleton [30,[39][40][41][42]. Bartunek et al [43] propose a method for minutiae extraction from the skeleton using the neural network.…”