Dorsal hand-vein recognition has been widely applied in security, and particularly authentication. In the past decade, various palmprint recognition methods have been proposed and achieved promising recognition performance. However, most of these methods require rich priori knowledge and cannot adapt well to different palmprint recognition scenarios, including contact-based, contactless and multispectral palmprint recognition. This problem limits the application and popularization of dorsal hand-vein recognition. In this chapter, motivated by least square regression (LSR), we propose a salient and discriminative descriptor learning method (SDDLM) for general scenario dorsal hand-vein recognition. Different from the conventional dorsal hand-vein feature extraction methods, SDDLM jointly learns noise and salient information from the pixels of dorsal hand-vein images, simultaneously. The learned noise enforces the projection matrix to learn salient and discriminative features from each palmprint sample. Thus, SDDLM can be adaptive to multi-scenarios. Experiments were conducted on the palm vein and dorsal hand vein databases. It can be seen from the experimental results that the proposed SDDLM consistently outperformed the classical dorsal hand-vein recognition methods and state-of-the-art methods for dorsal hand-vein recognition.