**2. Problem Definition**

Users' hand-geometry-based identification systems can (on the basis of the image scanning evaluation method adopted) be categorized into three distinct types.


natural shape. This way, unwanted deformations are eliminated [36]. In their work, [36] the researchers adopted a tabular scanner without pins fixed on it.


A novel way to identify or verify a person's identity is by detecting the distribution of veins around the wrist or on the palm surface. The main advantage of this approach is the difficulty in replicating or fabricating the human vein, since the vessels are hidden in the body. References [38] described two possible scanning methods in this regard, which include far infrared (FIR) and near infrared (NIR) [39,40]. FIR is a technology that scans thermal radiation with a wavelength of 15 to 1000 μm of the object (an individual's wrist or palm surface) under examination. A number of external and internal conditions influence FIR. For instance, temperature and/or moisture of the external environment as well as existing health conditions of the scanned individual can influence its sensitivity. Consequently, the scanned image may be unreliable. NIR on the other uses infrared radiation of the wavelength range of 0.76–1.4 μm of the scanned tissue(s). The technology has a penetration range of approximately 3 mm. Deoxidized hemoglobin found in the veins has the tendency to absorb maximum radiation with a wavelength range between 7.6 × 10−<sup>4</sup> mm [41]. IR (Infra Red) radiation absorption increases with large veins as compared to tissues adjacent to it [42,43]. As such, the contrast between the object under investigation (large veins) and surrounding objects (tissue) is easily accomplished. Two essential conditions for effective near infrared biometric technology are appropriate camera with IR filter and suitable lighting of the area that uses the IR radiation source. Furthermore, a primary benefit of NIR technology is that the external and internal conditions do not affect the image scanning process. The process is also not affected by skin deviations and tones of the image.

In the light of the foregone analysis on biometric verification and identification, the current study aims at designing an experimental multi-biometric verification system, which is based on two biometric characteristics: hand geometry and blood flow from the upper part of the hand. Since it has been established in literature that a combination of two biometric features provide better verification and identification results. The proposed system has been selected on the basis that it is impossible to integrate the appraisal on coarse data level (sensor-level fusion) as well as on features absent on a collected biometric characteristics level (Feature-Level Fusion) [6,44]. Additionally, due to the vast misunderstanding between identification, verification, and authentication biometric devices [45], it is important to clarify that the proposed system is a verification system, which checks a user's biometric identity against those of a number of persons within a database (Figure 1) [45–47].

**Figure 1.** Schematic representation of the proposed identification and verification system.
