Soft biometric traits refer to physical and behavioral traits, such as gender, height and weight, which are not unique to a specific subject, but are useful for identification, verification, and description of human subjects. Soft biometric attributes can be combined with classical biometric traits to improve the accuracy of a biometric recognition system. They can also be used as filters to restrict the search during a biometric identification operation. The extraction of soft biometric attributes can also be useful in other application domains, such as healthcare, human computer interaction (HCI), robotics, and gaming. This special issue aims to assemble high-quality, unpublished research papers on the topic of soft biometric extraction and matching based on image and video data.
Edited by: Guodong Guo, Mark Nixon, Arun Ross and Mayank Vatsa