Palm-Vein Recognition Using RGB Images

Palm-Vein Verification Using Images From the Visible Spectrum

“…where 0 0 0 and I I I denote respectively the zero and the identity matrices. A projection operation on an image X X X by k pixels of shift to the horizontal direction is obtained by [11]- [14], [16]- [20], [22], [52], [53] (c) Nil Palmprint (d) [23], [24], [27]- [30] (e) [54] (f) [25], [26], [31]- [36] Palm-vein + palmprint (g) [55] (h) [15], [48], [56]- [58] (i) [50] a : The conference presentation [21] was a preliminary work of the current proposal. b : The current manuscript has lower than 10% of content overlap with that of [21].…”

“…It has been shown that extraction of palm-vein using the RGB images is a feasible approach since the wavelength of the Red channel is close to the NIR spectrum (see Table 1). As shown in Table 2 which covers a brief survey of RGB and NIR systems, only two researches [21], [55] (see cells (a) and (g) of the table) have verified this observation. In the bimodal work [55], the palm-vein lines were extracted by a vein and crease filter proposed by the authors.…”

“…This is due to the high penetrability of long wavelength of the IR and the NIR rays into the skin tissues to reach the blood vessels [17]. The RGB palm-vein is only partially visible due to the relatively low penetration of the visible imaging spectrum [21], [49], [50]. Although certain information can be lost, the partial information constitutes an additional attribute for biometric authentication.…”

“…This has been grounded on the observation of the width difference between the palmvein lines and palmprint creases. Our preliminary work [21] uses an efficient Gabor filtering for palm-vein line extraction. The result showed promising performance in terms of the EER.…”

“…This is differentiated from the conventional NIR based systems which require an NIR device for capturing the palm-vein. Also, different from [55] and [21], multi-direction and multi-scale palm-vein line features have been utilized for accurate verification. • A simple and yet efficient difference image projection for encoding the directional palm-vein line features.…”